| Title: | Statistical Analysis for Environmental Data |
|---|---|
| Description: | Statistical analysis methods for environmental data are implemented. There is a particular focus on robust methods, and on methods for compositional data. In addition, larger data sets from geochemistry are provided. The statistical methods are described in Reimann, Filzmoser, Garrett, Dutter (2008, ISBN:978-0-470-98581-6). |
| Authors: | Peter Filzmoser [aut, cre, cph] |
| Maintainer: | Peter Filzmoser <[email protected]> |
| License: | GPL (>= 3) |
| Version: | 1.7.11 |
| Built: | 2025-01-27 04:10:41 UTC |
| Source: | https://github.com/cran/StatDA |
Adaptive reweighted estimator for multivariate location and scatter with hard-rejection weights. The multivariate outliers are defined according to the supremum of the difference between the empirical distribution function of the robust Mahalanobis distance and the theoretical distribution function.
arw(x, m0, c0, alpha, pcrit)arw(x, m0, c0, alpha, pcrit)
x |
Dataset (n x p) |
m0 |
Initial location estimator (1 x p) |
c0 |
Initial scatter estimator (p x p) |
alpha |
Maximum thresholding proportion (optional scalar, default: alpha = 0.025) |
pcrit |
Critical value obtained by simulations (optional scalar, default value obtained from simulations) |
At the basis of initial estimators of location and scatter, the function arw performs a reweighting step to adjust the threshold for outlier rejection. The critical value pcrit was obtained by simulations using the MCD estimator as initial robust covariance estimator. If a different estimator is used, pcrit should be changed and computed by simulations for the specific dimensions of the data x.
m |
Adaptive location estimator (p x 1) |
c |
Adaptive scatter estimator (p x p) |
cn |
Adaptive threshold ("adjusted quantile") |
w |
Weight vector (n x 1) |
Moritz Gschwandtner <[email protected]>
Peter Filzmoser <[email protected]>
http://cstat.tuwien.ac.at/filz/
P. Filzmoser, R.G. Garrett, and C. Reimann (2005). Multivariate outlier detection in exploration geochemistry. Computers & Geosciences, 31:579-587.
x <- cbind(rnorm(100), rnorm(100)) arw(x, apply(x,2,mean), cov(x))x <- cbind(rnorm(100), rnorm(100)) arw(x, apply(x,2,mean), cov(x))
Au data from Kola C-horizon, new measurement method
data(AuNEW)data(AuNEW)
The format is: num [1:606] 0.001344 0.000444 0.001607 0.000713 0.000898 ...
These data of Au have much higher quality than the data AuOLD.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(AuNEW) data(AuOLD) plot(log10(AuOLD),log10(AuNEW))data(AuNEW) data(AuOLD) plot(log10(AuOLD),log10(AuNEW))
Au data from Kola C-horizon, old measurement method
data(AuOLD)data(AuOLD)
The format is: num [1:606] 0.001 0.001 0.002 0.001 0.007 0.006 0.001 0.001 0.001 0.001 ...
These data of Au have much worse quality than the data AuNEW.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(AuNEW) data(AuOLD) plot(log10(AuOLD),log10(AuNEW))data(AuNEW) data(AuOLD) plot(log10(AuOLD),log10(AuNEW))
The Kola Data were collected in the Kola Project (1993-1998, Geological Surveys of Finland (GTK) and Norway (NGU) and Central Kola Expedition (CKE), Russia). More than 600 samples in five different layers were analysed, this dataset contains the B-horizon.
data(bhorizon)data(bhorizon)
A data frame with 609 observations on the following 77 variables.
IDa numeric vector
XCOOa numeric vector
YCOOa numeric vector
ELEVa numeric vector
COUNa factor with levels FIN NOR RUS
ASPa factor with levels E FLAT N NE NW NW S SE SW W
LOWDBa numeric vector
LITOa numeric vector
GENLANa factor with levels DEEPVAL FLA PLAIN FLAT HIMO LOWMO PLAIN PLAT RIDGE SLOPE
Aga numeric vector
Ala numeric vector
Al_XRFa numeric vector
Al2O3a numeric vector
Asa numeric vector
Aua numeric vector
Ba numeric vector
Baa numeric vector
Bea numeric vector
Bia numeric vector
Br_ICa numeric vector
Caa numeric vector
Ca_XRFa numeric vector
CaOa numeric vector
Cda numeric vector
Cl_ICa numeric vector
Coa numeric vector
Cra numeric vector
Cua numeric vector
ECa numeric vector
F_ICa numeric vector
Fea numeric vector
Fe_XRFa numeric vector
Fe2O3a numeric vector
Hga numeric vector
Ka numeric vector
K_XRFa numeric vector
K2Oa numeric vector
Laa numeric vector
Lia numeric vector
LOIa numeric vector
Mga numeric vector
Mg_XRFa numeric vector
MgOa numeric vector
Mna numeric vector
Mn_XRFa numeric vector
MnOa numeric vector
Moa numeric vector
Naa numeric vector
Na_XRFa numeric vector
Na2Oa numeric vector
Nia numeric vector
NO3_ICa numeric vector
Pa numeric vector
P_XRFa numeric vector
P2O5a numeric vector
Pba numeric vector
Pda numeric vector
pHa numeric vector
PO4_ICa numeric vector
Pta numeric vector
Sa numeric vector
Sba numeric vector
Sca numeric vector
Sea numeric vector
Sia numeric vector
Si_XRFa numeric vector
SiO2a numeric vector
SO4_ICa numeric vector
Sra numeric vector
Tea numeric vector
Tha numeric vector
Tia numeric vector
Ti_XRFa numeric vector
TiO2a numeric vector
Va numeric vector
Ya numeric vector
Zna numeric vector
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
Kola Project (1993-1998)
Reimann C, ?yr?s M, Chekushin V, Bogatyrev I, Boyd R, Caritat P de, Dutter R, Finne TE, Halleraker JH, J?ger ?, Kashulina G, Lehto O, Niskavaara H, Pavlov V, R?is?nen ML, Strand T, Volden T. Environmental Geochemical Atlas of the Central Barents Region. NGU-GTK-CKE Special Publication, Geological Survey of Norway, Trondheim, Norway, 1998.
data(bhorizon) str(bhorizon)data(bhorizon) str(bhorizon)
x- and y-coordinates of the Kola Project boundary.
data(bordersKola)data(bordersKola)
The format is: List of 2 $ x: num [1:64] 836200 881000 752900 743100 737500 ... $ y: num [1:64] 7708867 7403003 7389239 7377769 7364006 ...
The corrdinates for the Kola Project boundary are used for the surface maps, i.e. for Krige and Smoothing maps. It is a list with two list elements x and y for the x- and y-coordinates.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(bordersKola) plot(bordersKola$x,bordersKola$y)data(bordersKola) plot(bordersKola$x,bordersKola$y)
The function boxes computes boxes of multivariate data. If add=TRUE the boxes are plotted in the current plot otherwise nothing is plotted.
boxes(x, xA = 1, yA = 2, zA = 3, labels = dimnames(x)[[1]], locations = NULL, nrow = NULL, ncol = NULL, key.loc = NULL, key.labels = dimnames(x)[[2]], key.xpd = TRUE, xlim = NULL, ylim = NULL, flip.labels = NULL, len = 1, leglen = 1, axes = FALSE, frame.plot = axes, main = NULL, sub = NULL, xlab = "", ylab = "", cex = 0.8, lwd = 0.25, lty = par("lty"), xpd = FALSE, mar = pmin(par("mar"), 1.1 + c(2 * axes + (xlab != ""), 2 * axes + (ylab != ""), 1, 0)), add = FALSE, plot = TRUE, ...)boxes(x, xA = 1, yA = 2, zA = 3, labels = dimnames(x)[[1]], locations = NULL, nrow = NULL, ncol = NULL, key.loc = NULL, key.labels = dimnames(x)[[2]], key.xpd = TRUE, xlim = NULL, ylim = NULL, flip.labels = NULL, len = 1, leglen = 1, axes = FALSE, frame.plot = axes, main = NULL, sub = NULL, xlab = "", ylab = "", cex = 0.8, lwd = 0.25, lty = par("lty"), xpd = FALSE, mar = pmin(par("mar"), 1.1 + c(2 * axes + (xlab != ""), 2 * axes + (ylab != ""), 1, 0)), add = FALSE, plot = TRUE, ...)
x |
multivariate data in form of matrix or data frame |
xA |
assignment of clusters to the coordinates of the boxes |
yA |
assignment of clusters to the coordinates of the boxes |
zA |
assignment of clusters to the coordinates of the boxes |
labels |
vector of character strings for labeling the plots |
locations |
locations for the boxes on the plot (e.g. X/Y coordinates) |
nrow |
integers giving the number of rows ands columns to use when 'locations' is 'NULL'. By default, 'nrow == ncol', a square will be used. |
ncol |
integers giving the number of rows and columns to use when 'locations' is 'NULL'. By default, 'nrow == ncol', a square will be used. |
key.loc |
vector with x and y coordinates of the unit key. |
key.labels |
vector of character strings for labeling the segments of the unit key. If omitted, the second component of 'dimnames(x)' ist used, if available. |
key.xpd |
clipping switch for the unit key (drawing and labeling), see 'par("xpd")'. |
xlim |
vector with the range of x coordinates to plot |
ylim |
vector with the range of y coordinates to plot |
flip.labels |
logical indicating if the label locations should flip up and down from diagram to diagram. Defaults to a somewhat smart heuristic. |
len |
multiplicative values for the space used in the plot window |
leglen |
multiplicative values for the space of the labels on the legend |
axes |
logical flag: if 'TRUE' axes are added to the plot |
frame.plot |
logical flag: if 'TRUE', the plot region ist framed |
main |
a main title for the plot |
sub |
a sub title for the plot |
xlab |
a label for the x axis |
ylab |
a label for the y axis |
cex |
character expansion factor for the labels |
lwd |
line width used for drawing |
lty |
line type used for drawing |
xpd |
logical or NA indicationg if clipping should be done, see 'par(xpd=.)' |
mar |
argument to 'par(mar=*)', rypically choosing smaller margings than by default |
add |
logical, if 'TRUE' add boxes to current plot |
plot |
logical, if 'FALSE', nothing is plotted |
... |
further arguments, passed to the first call of 'plot()' |
This type of graphical approach for multivariate data is only applicable where the data can be grouped into three clusters. This means that before the plot can be made the data undergo a hierarchical cluster to get the size of each cluster. The distance measure for the hierarchicla cluster is complete linkage. Each cluster represents one side of the boxes.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
#plots the background and the boxes for the elements data(ohorizon) X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] el=log10(ohorizon[,c("Co","Cu","Ni","Rb","Bi","Na","Sr")]) data(kola.background) sel <- c(3,8,22, 29, 32, 35, 43, 69, 73 ,93,109,129,130,134,168,181,183,205,211, 218,237,242,276,292,297,298,345,346,352,372,373,386,408,419,427,441,446,490, 516,535,551,556,558,564,577,584,601,612,617) x=el[sel,] xwid=diff(range(X))/12e4 ywid=diff(range(Y))/12e4 plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n", xlim=c(360000,max(X))) plotbg(map.col=c("gray","gray","gray","gray"),add.plot=TRUE) boxes(x,locations=cbind(X[sel],Y[sel]),len=20000,key.loc=c(800000,7830000),leglen=25000, cex=0.75, add=TRUE, labels=NULL, lwd=1.1)#plots the background and the boxes for the elements data(ohorizon) X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] el=log10(ohorizon[,c("Co","Cu","Ni","Rb","Bi","Na","Sr")]) data(kola.background) sel <- c(3,8,22, 29, 32, 35, 43, 69, 73 ,93,109,129,130,134,168,181,183,205,211, 218,237,242,276,292,297,298,345,346,352,372,373,386,408,419,427,441,446,490, 516,535,551,556,558,564,577,584,601,612,617) x=el[sel,] xwid=diff(range(X))/12e4 ywid=diff(range(Y))/12e4 plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n", xlim=c(360000,max(X))) plotbg(map.col=c("gray","gray","gray","gray"),add.plot=TRUE) boxes(x,locations=cbind(X[sel],Y[sel]),len=20000,key.loc=c(800000,7830000),leglen=25000, cex=0.75, add=TRUE, labels=NULL, lwd=1.1)
This function plots the legend in form of a boxplot. The symbols represent the different levels (e.g. whiskers, median, ...) of the boxplot.
boxplotlegend(X, Y, el, boxinfo, x.shift = 40000, xf = 10000, y.shift = 0.2, y.scale = 130000, legend.title = "Legend", cex.legtit = 1, logscale = TRUE, symb = c(1, 1, 16, 3, 3), ssize = c(1.5, 1, 0.3, 1, 1.5), accentuate = FALSE, cex.scale = 0.8)boxplotlegend(X, Y, el, boxinfo, x.shift = 40000, xf = 10000, y.shift = 0.2, y.scale = 130000, legend.title = "Legend", cex.legtit = 1, logscale = TRUE, symb = c(1, 1, 16, 3, 3), ssize = c(1.5, 1, 0.3, 1, 1.5), accentuate = FALSE, cex.scale = 0.8)
X |
X-coordinates |
Y |
Y-coordinates |
el |
variable considered |
boxinfo |
from boxplot(el) or boxplotlog(el) |
x.shift |
shift in x-direction |
xf |
width in x-direction |
y.shift |
shift in y-direction (from title) |
y.scale |
scale in y-direction |
legend.title |
title for legend |
cex.legtit |
cex of title for legend |
logscale |
if TRUE plot boxplot in log-scale |
symb |
symbols to be used (length 5!) |
ssize |
symbol sizes to be used (length 5!) |
accentuate |
if FALSE no symbols for the upper values (e.g. upper "hinge", upper whisker) are assigned |
cex.scale |
cex for text "log-scale" for scale |
Takes the information provided by the argument boxinfo and plots a boxplot corresponding to the values. If there are no upper or/and lower outliers the symbols for the upper or/and lower whiskers will be ignored.
Plots the legend with respect to the boxplot and returns the symbols, size and the quantiles used for the legend.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
#internal function, used in SymbLegend#internal function, used in SymbLegend
The function boxplot plots a boxplot of the data with respect to the logarithmic transformed values of the whiskers. See also details.
boxplotlog(x, ..., range = 1.5, width = NULL, varwidth = FALSE, notch = FALSE, outline = TRUE, names, plot = TRUE, border = par("fg"), col = NULL, log = "", pars = list(boxwex = 0.8, staplewex = 0.5, outwex = 0.5), horizontal = FALSE, add = FALSE, at = NULL)boxplotlog(x, ..., range = 1.5, width = NULL, varwidth = FALSE, notch = FALSE, outline = TRUE, names, plot = TRUE, border = par("fg"), col = NULL, log = "", pars = list(boxwex = 0.8, staplewex = 0.5, outwex = 0.5), horizontal = FALSE, add = FALSE, at = NULL)
x |
data |
... |
further arguments for creating the list |
range |
this determines how far the plot "whiskers" extend from the box. If range is positive, the most extreme data point which is no more than range times the length of the box away from the box. A value of zero causes the whiskers to extend to the data extremes. |
width |
a vector giving the relative widths of the boxes making up the plot |
varwidth |
if varwidth is TRUE, the boxes are drawn with widths proportional to the square-roots of the number of observations in the groups. |
notch |
if notch is TRUE, a notch is drawn in each side of the boxes |
outline |
if outline is FALSE, the outliers are not drawn |
names |
define the names of the attributes |
plot |
if plot is TRUE the boxplot is plotted in the current plot |
border |
character or numeric (vector) which indicates the color of the box borders |
col |
defines the colour |
log |
character, indicating if any axis should be drawn in logarithmic scale |
pars |
some graphical parameters can be specified |
horizontal |
logical parameter indicating if the boxplots should be horizontal; FALSE means vertical boxes |
add |
if TRUE the boxplot is added to the current plot |
at |
numeric vector giving the locations of the boxplots |
Sometimes a boxplot of the original data does not identify outliers because the boxplot assumes normal distribution. Therefore the data are logarithmically transformed and values for plotting the boxplot are calculated. After that the data are backtransformed and the boxplot is plotted with respect to the logarithmic results. Now the outliers are identified.
stats |
a vector of length 5, containing the extreme of the lower whisker, the lower "hinge", the median, the upper "hinge" and the extreme of the upper whisker (backtransformed) |
n |
the number of non-NA observations in the sample |
conf |
the lower and upper extremes of the "notch" |
out |
the values of any data points which lie beyond the extremes of the whiskers (backtransformed) |
group |
the group |
names |
the attributes |
Returns a boxplot which is calculated with the log-transformed data.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(chorizon) Ba=chorizon[,"Ba"] boxplotlog((Ba),horizontal=TRUE,xlab="Ba [mg/kg]",cex.lab=1.4,pch=3,cex=1.5)data(chorizon) Ba=chorizon[,"Ba"] boxplotlog((Ba),horizontal=TRUE,xlab="Ba [mg/kg]",cex.lab=1.4,pch=3,cex=1.5)
This function plots a boxplot of the data and the boundaries are based on percentiles.
boxplotperc(x, ..., quant = c(0.02, 0.98), width = NULL, varwidth = FALSE, notch = FALSE, outline = TRUE, names, plot = TRUE, border = par("fg"), col = NULL, log = "", pars = list(boxwex = 0.8, staplewex = 0.5, outwex = 0.5), horizontal = FALSE, add = FALSE, at = NULL)boxplotperc(x, ..., quant = c(0.02, 0.98), width = NULL, varwidth = FALSE, notch = FALSE, outline = TRUE, names, plot = TRUE, border = par("fg"), col = NULL, log = "", pars = list(boxwex = 0.8, staplewex = 0.5, outwex = 0.5), horizontal = FALSE, add = FALSE, at = NULL)
x |
data |
... |
further arguments for creating the list |
quant |
the underlying percentages |
width |
a vector giving the relative widths of the boxes making up the plot |
varwidth |
if varwidth is TRUE, the boxes are drawn with widths proportional to the square-roots of the number of observations in the groups. |
notch |
if notch is TRUE, a notch is drawn in each side of the boxes |
outline |
if outliers is FALSE, the outliers are not drawn |
names |
define the names of the attributes |
plot |
if plot is TRUE the boxplot is plotted in the current plot |
border |
character or numeric (vector) which indicates the color of the box borders |
col |
defines the colour |
log |
character, indicating if any axis should be drawn in logarithmic scale |
pars |
some graphical parameters can be specified |
horizontal |
logical parameter indicating if the boxplots should be horizontal; FALSE means vertical boxes |
add |
if TRUE the boxplot is added to the current plot |
at |
numeric vector giving the locations of the boxplots |
The default value for quant is the 2% and 98% quantile and this argument defines the percentiles for the upper and lower whiskers.
stats |
a vector of length 5, containing the extreme of the lower whisker, the lower "hinge", the median, the upper "hinge" and the extreme of the upper whisker (backtransformed) |
n |
the number of non-NA observations in the sample |
conf |
the lower and upper extremes of the "notch" |
out |
the values of any data points which lie beyond the extremes of the whiskers (backtransformed) |
group |
the group |
names |
the attributes |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(chorizon) Ba=chorizon[,"Ba"] boxplotperc(Ba,quant=c(0.05,0.95),horizontal=TRUE,xlab="Ba [mg/kg]",cex.lab=1.2,pch=3)data(chorizon) Ba=chorizon[,"Ba"] boxplotperc(Ba,quant=c(0.05,0.95),horizontal=TRUE,xlab="Ba [mg/kg]",cex.lab=1.2,pch=3)
This function plots multivariate data with respect to the value. The size of the bubble represents the value of the datapoint.
bubbleFIN(x, y, z, radi = 10000, S = 9, s = 0.9, wa = 0, wb = 0.95, wc = 0.05, plottitle = "BubblePlot", legendtitle = "Legend", text.cex = 1, legtitle.cex = 1, backgr = "kola.background", leg = TRUE, ndigits = 1)bubbleFIN(x, y, z, radi = 10000, S = 9, s = 0.9, wa = 0, wb = 0.95, wc = 0.05, plottitle = "BubblePlot", legendtitle = "Legend", text.cex = 1, legtitle.cex = 1, backgr = "kola.background", leg = TRUE, ndigits = 1)
x |
x coordinates |
y |
y coordinates |
z |
measured value at point (x,y) |
radi |
scaling for the map |
S, s
|
control the size of the largest and smallest bubbles |
wa, wb, wc
|
factors which defines the shape of the exponential function |
plottitle |
the titel of the plot |
legendtitle |
the titel of the legend |
text.cex |
multiplier for the size of the labels |
legtitle.cex |
multiplier for the size of the legendtitle |
backgr |
which background should be used |
leg |
if TRUE the bubbles are plotted to the legend |
ndigits |
how much digits should be plotted at the legend |
The smallest bubbles represent the 10% quantile and the biggest bubbles represent the 99
Plots bubbles in the existing plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(kola.background) data(ohorizon) el=ohorizon[,"Mg"] X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n") #plot bubbles with background plotbg(map.col=c("gray","gray","gray","gray"),add.plot=TRUE) bubbleFIN(X,Y,el,S=9,s=2,plottitle="",legendtitle="Mg [mg/kg]", text.cex=0.63,legtitle.cex=0.80)data(kola.background) data(ohorizon) el=ohorizon[,"Mg"] X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n") #plot bubbles with background plotbg(map.col=c("gray","gray","gray","gray"),add.plot=TRUE) bubbleFIN(X,Y,el,S=9,s=2,plottitle="",legendtitle="Mg [mg/kg]", text.cex=0.63,legtitle.cex=0.80)
Analytical duplicates have been selected for quality control.
data(CHorANADUP)data(CHorANADUP)
A data frame with 52 observations on the following 190 variables.
A1_.Loca numeric vector
A2_.Loca numeric vector
A1_Aga numeric vector
A1_Ag_INAAa numeric vector
A1_Ala numeric vector
A1_Al2O3a numeric vector
A1_Asa numeric vector
A1_As_INAAa numeric vector
A1_Au_INAAa numeric vector
A1_Ba numeric vector
A1_Baa numeric vector
A1_Ba_INAAa numeric vector
A1_Bea numeric vector
A1_Bia numeric vector
A1_Bra numeric vector
A1_Br_INAAa numeric vector
A1_Caa numeric vector
A1_Ca_INAAa numeric vector
A1_CaOa numeric vector
A1_Cda numeric vector
A1_Ce_INAAa numeric vector
A1_Cla numeric vector
A1_Coa numeric vector
A1_Co_INAAa numeric vector
A1_Conda numeric vector
A1_Cra numeric vector
A1_Cr_INAAa numeric vector
A1_Cs_INAAa numeric vector
A1_Cua numeric vector
A1_Eu_INAAa numeric vector
A1_Fa numeric vector
A1_F_ionselecta numeric vector
A1_Fea numeric vector
A1_Fe_INAAa numeric vector
A1_Fe2O3a numeric vector
A1_Hf_INAAa numeric vector
A1_Hga numeric vector
A1_Hg_INAAa numeric vector
A1_Ir_INAAa numeric vector
A1_Ka numeric vector
A1_K2Oa numeric vector
A1_Laa numeric vector
A1_La_INAAa numeric vector
A1_Lia numeric vector
A1_LOIa numeric vector
A1_Lu_INAAa numeric vector
A1_Mass_INAAa numeric vector
A1_Mga numeric vector
A1_MgOa numeric vector
A1_Mna numeric vector
A1_MnOa numeric vector
A1_Moa numeric vector
A1_Mo_INAAa numeric vector
A1_Naa numeric vector
A1_Na_INAAa numeric vector
A1_Na2Oa numeric vector
A1_Nd_INAAa numeric vector
A1_Nia numeric vector
A1_Ni_INAAa numeric vector
A1_NO2a numeric vector
A1_NO3a numeric vector
A1_Pa numeric vector
A1_P2O5a numeric vector
A1_Pba numeric vector
A1_pHa numeric vector
A1_PO4a numeric vector
A1_Rba numeric vector
A1_Sa numeric vector
A1_Sba numeric vector
A1_Sb_INAAa numeric vector
A1_Sca numeric vector
A1_Sc_INAAa numeric vector
A1_Sea numeric vector
A1_Se_INAAa numeric vector
A1_Sia numeric vector
A1_SiO2a numeric vector
A1_Sm_INAAa numeric vector
A1_Sn_INAAa numeric vector
A1_SO4a numeric vector
A1_Sra numeric vector
A1_Sr_INAAa numeric vector
A1_Suma numeric vector
A1_Ta_INAAa numeric vector
A1_Tb_INAAa numeric vector
A1_Tea numeric vector
A1_Tha numeric vector
A1_Th_INAAa numeric vector
A1_Tia numeric vector
A1_TiO2a numeric vector
A1_U_INAAa numeric vector
A1_Va numeric vector
A1_W_INAAa numeric vector
A1_Ya numeric vector
A1_Yb_INAAa numeric vector
A1_Zna numeric vector
A1_Zn_INAAa numeric vector
A2_Aga numeric vector
A2_Ag_INAAa numeric vector
A2_Ala numeric vector
A2_Al2O3a numeric vector
A2_Asa numeric vector
A2_As_INAAa numeric vector
A2_Au_INAAa numeric vector
A2_Ba numeric vector
A2_Baa numeric vector
A2_Ba_INAAa numeric vector
A2_Bea numeric vector
A2_Bia numeric vector
A2_Bra numeric vector
A2_Br_INAAa numeric vector
A2_Caa numeric vector
A2_Ca_INAAa numeric vector
A2_CaOa numeric vector
A2_Cda numeric vector
A2_Ce_INAAa numeric vector
A2_Cla numeric vector
A2_Coa numeric vector
A2_Co_INAAa numeric vector
A2_Conda numeric vector
A2_Cra numeric vector
A2_Cr_INAAa numeric vector
A2_Cs_INAAa numeric vector
A2_Cua numeric vector
A2_Eu_INAAa numeric vector
A2_Fa numeric vector
A2_F_ionselecta numeric vector
A2_Fea numeric vector
A2_Fe_INAAa numeric vector
A2_Fe2O3a numeric vector
A2_Hf_INAAa numeric vector
A2_Hga numeric vector
A2_Hg_INAAa numeric vector
A2_Ir_INAAa numeric vector
A2_Ka numeric vector
A2_K2Oa numeric vector
A2_Laa numeric vector
A2_La_INAAa numeric vector
A2_Lia numeric vector
A2_LOIa numeric vector
A2_Lu_INAAa numeric vector
A2_Mass_INAAa numeric vector
A2_Mga numeric vector
A2_MgOa numeric vector
A2_Mna numeric vector
A2_MnOa numeric vector
A2_Moa numeric vector
A2_Mo_INAAa numeric vector
A2_Naa numeric vector
A2_Na_INAAa numeric vector
A2_Na2Oa numeric vector
A2_Nd_INAAa numeric vector
A2_Nia numeric vector
A2_Ni_INAAa numeric vector
A2_NO2a numeric vector
A2_NO3a numeric vector
A2_Pa numeric vector
A2_P2O5a numeric vector
A2_Pba numeric vector
A2_pHa numeric vector
A2_PO4a numeric vector
A2_Rba numeric vector
A2_Sa numeric vector
A2_Sba numeric vector
A2_Sb_INAAa numeric vector
A2_Sca numeric vector
A2_Sc_INAAa numeric vector
A2_Sea numeric vector
A2_Se_INAAa numeric vector
A2_Sia numeric vector
A2_SiO2a numeric vector
A2_Sm_INAAa numeric vector
A2_Sn_INAAa numeric vector
A2_SO4a numeric vector
A2_Sra numeric vector
A2_Sr_INAAa numeric vector
A2_Suma numeric vector
A2_Ta_INAAa numeric vector
A2_Tb_INAAa numeric vector
A2_Tea numeric vector
A2_Tha numeric vector
A2_Th_INAAa numeric vector
A2_Tia numeric vector
A2_TiO2a numeric vector
A2_U_INAAa numeric vector
A2_Va numeric vector
A2_W_INAAa numeric vector
A2_Ya numeric vector
A2_Yb_INAAa numeric vector
A2_Zna numeric vector
A2_Zn_INAAa numeric vector
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
Kola Project (1993-1998)
Reimann C, ?yr?s M, Chekushin V, Bogatyrev I, Boyd R, Caritat P de, Dutter R, Finne TE, Halleraker JH, J?ger ?, Kashulina G, Lehto O, Niskavaara H, Pavlov V, R?is?nen ML, Strand T, Volden T. Environmental Geochemical Atlas of the Central Barents Region. NGU-GTK-CKE Special Publication, Geological Survey of Norway, Trondheim, Norway, 1998.
data(CHorANADUP) str(CHorANADUP)data(CHorANADUP) str(CHorANADUP)
Field duplicates have been selected for quality control.
data(CHorFieldDUP)data(CHorFieldDUP)
A data frame with 49 observations on the following 240 variables.
F1_.Loca numeric vector
F2_.Loca numeric vector
XCOOa numeric vector
YCOOa numeric vector
F1_Aga numeric vector
F1_Ag_INAAa numeric vector
F1_Ala numeric vector
F1_Al2O3a numeric vector
F1_Asa numeric vector
F1_As_INAAa numeric vector
F1_Au_INAAa numeric vector
F1_Ba numeric vector
F1_Baa numeric vector
F1_Ba_INAAa numeric vector
F1_Bea numeric vector
F1_Bia numeric vector
F1_Bra numeric vector
F1_Br_INAAa numeric vector
F1_Caa numeric vector
F1_Ca_INAAa numeric vector
F1_CaOa numeric vector
F1_Cda numeric vector
F1_Ce_INAAa numeric vector
F1_Cla numeric vector
F1_Coa numeric vector
F1_Co_INAAa numeric vector
F1_Conda numeric vector
F1_Cra numeric vector
F1_Cr_INAAa numeric vector
F1_Cs_INAAa numeric vector
F1_Cua numeric vector
F1_Eu_INAAa numeric vector
F1_Fa numeric vector
F1_F_ionselecta numeric vector
F1_Fea numeric vector
F1_Fe_INAAa numeric vector
F1_Fe2O3a numeric vector
F1_Hf_INAAa numeric vector
F1_Hga numeric vector
F1_Hg_INAAa numeric vector
F1_Ir_INAAa numeric vector
F1_Ka numeric vector
F1_K2Oa numeric vector
F1_Laa numeric vector
F1_La_INAAa numeric vector
F1_Lia numeric vector
F1_LOIa numeric vector
F1_Lu_INAAa numeric vector
F1_Mass_INAAa numeric vector
F1_Mga numeric vector
F1_MgOa numeric vector
F1_Mna numeric vector
F1_MnOa numeric vector
F1_Moa numeric vector
F1_Mo_INAAa numeric vector
F1_Naa numeric vector
F1_Na_INAAa numeric vector
F1_Na2Oa numeric vector
F1_Nd_INAAa numeric vector
F1_Nia numeric vector
F1_Ni_INAAa numeric vector
F1_NO2a numeric vector
F1_NO3a numeric vector
F1_Pa numeric vector
F1_P2O5a numeric vector
F1_Pba numeric vector
F1_pHa numeric vector
F1_PO4a numeric vector
F1_Rba numeric vector
F1_Sa numeric vector
F1_Sba numeric vector
F1_Sb_INAAa numeric vector
F1_Sca numeric vector
F1_Sc_INAAa numeric vector
F1_Sea numeric vector
F1_Se_INAAa numeric vector
F1_Sia numeric vector
F1_SiO2a numeric vector
F1_Sm_INAAa numeric vector
F1_Sn_INAAa numeric vector
F1_SO4a numeric vector
F1_Sra numeric vector
F1_Sr_INAAa numeric vector
F1_Suma numeric vector
F1_Ta_INAAa numeric vector
F1_Tb_INAAa numeric vector
F1_Tea numeric vector
F1_Tha numeric vector
F1_Th_INAAa numeric vector
F1_Tia numeric vector
F1_TiO2a numeric vector
F1_U_INAAa numeric vector
F1_Va numeric vector
F1_W_INAAa numeric vector
F1_Ya numeric vector
F1_Yb_INAAa numeric vector
F1_Zna numeric vector
F1_Zn_INAAa numeric vector
F2_Aga numeric vector
F2_Ag_INAAa numeric vector
F2_Ala numeric vector
F2_Al2O3a numeric vector
F2_Asa numeric vector
F2_As_INAAa numeric vector
F2_Au_INAAa numeric vector
F2_Ba numeric vector
F2_Baa numeric vector
F2_Ba_INAAa numeric vector
F2_Bea numeric vector
F2_Bia numeric vector
F2_Bra numeric vector
F2_Br_INAAa numeric vector
F2_Caa numeric vector
F2_Ca_INAAa numeric vector
F2_CaOa numeric vector
F2_Cda numeric vector
F2_Ce_INAAa numeric vector
F2_Cla numeric vector
F2_Coa numeric vector
F2_Co_INAAa numeric vector
F2_Conda numeric vector
F2_Cra numeric vector
F2_Cr_INAAa numeric vector
F2_Cs_INAAa numeric vector
F2_Cua numeric vector
F2_Eu_INAAa numeric vector
F2_Fa numeric vector
F2_F_ionselecta numeric vector
F2_Fea numeric vector
F2_Fe_INAAa numeric vector
F2_Fe2O3a numeric vector
F2_Hf_INAAa numeric vector
F2_Hga numeric vector
F2_Hg_INAAa numeric vector
F2_Ir_INAAa numeric vector
F2_Ka numeric vector
F2_K2Oa numeric vector
F2_Laa numeric vector
F2_La_INAAa numeric vector
F2_Lia numeric vector
F2_LOIa numeric vector
F2_Lu_INAAa numeric vector
F2_Mass_INAAa numeric vector
F2_Mga numeric vector
F2_MgOa numeric vector
F2_Mna numeric vector
F2_MnOa numeric vector
F2_Moa numeric vector
F2_Mo_INAAa numeric vector
F2_Naa numeric vector
F2_Na_INAAa numeric vector
F2_Na2Oa numeric vector
F2_Nd_INAAa numeric vector
F2_Nia numeric vector
F2_Ni_INAAa numeric vector
F2_NO2a numeric vector
F2_NO3a numeric vector
F2_Pa numeric vector
F2_P2O5a numeric vector
F2_Pba numeric vector
F2_pHa numeric vector
F2_PO4a numeric vector
F2_Rba numeric vector
F2_Sa numeric vector
F2_Sba numeric vector
F2_Sb_INAAa numeric vector
F2_Sca numeric vector
F2_Sc_INAAa numeric vector
F2_Sea numeric vector
F2_Se_INAAa numeric vector
F2_Sia numeric vector
F2_SiO2a numeric vector
F2_Sm_INAAa numeric vector
F2_Sn_INAAa numeric vector
F2_SO4a numeric vector
F2_Sra numeric vector
F2_Sr_INAAa numeric vector
F2_Suma numeric vector
F2_Ta_INAAa numeric vector
F2_Tb_INAAa numeric vector
F2_Tea numeric vector
F2_Tha numeric vector
F2_Th_INAAa numeric vector
F2_Tia numeric vector
F2_TiO2a numeric vector
F2_U_INAAa numeric vector
F2_Va numeric vector
F2_W_INAAa numeric vector
F2_Ya numeric vector
F2_Yb_INAAa numeric vector
F2_Zna numeric vector
F2_Zn_INAAa numeric vector
DATEa numeric vector
X.SAMPa factor with levels CRJHPC CRPCTF CRTF GKJHOJ GKJHTV JARR JHOJTV M?VG MLRJARP MLRJSRR MLRM?DR OJGKTV RPAV RPMLRJA RPVM Semenov Smirnov VGM?
ELEVa numeric vector
UTMa numeric vector
X.COUNa factor with levels FIN NOR RUS
X.ASPa factor with levels E FLAT N NE NW S SE SW
X.GENLANa factor with levels FLAT LOWMO PLAIN RIDGE SLOPE
X.TOPOa factor with levels CONCLOW CONCMED CONVLOW CONVMED FLAT FLATLOW FLATTER LOWBRLOW LOWBRMED TER TERR TOP TOPFLAT TOPTER UPBRFLAT UPBRLOW UPBRMED UPBRTER
X.FORDENa factor with levels D MD MD NO S
X.TREESPEa factor with levels BI BI.. BI.PBET.JUN BI..PI .BI.SP BI..SP BI.SP. BI.S.PJUN NO P P. P.BI P.BIJUN P.BI.S .PIBI. PI.BI PI..BI PI.BI. .PIBI.SP PI..SP PI..SPBI P.SBI P.S.BI P.SBI.JUN S.BI S.BI.JUN SP..BI SP.BI. .SPBI.PI .SPPIBI.
TRHIGHa numeric vector
RELASa numeric vector
X.BUSHDENa factor with levels MD NO S
X.BUSHSPECa factor with levels BET BI ..BI .BI. BI.. .BI.JU BI..JU BI..PI JUN NO ..RO ..WI ..WIBI ..WIJU ..WIRO ..WIROJU
X.GRVEGETATIOa factor with levels B..CGML B..CH B.CO.GM B.CRCHMO.LIN B.CRGRMARMO.LI B.CRMO BJUO.MO.CR B.JUOMO.LI B.LINMAR B.MO.CRMAR .BO.ML C.. C..BGML C.B.GML .C.BGMLO C.B.GMLO C.B.L C.BL.GM C.BM.HGL C.BML.GO C.BO.G C.BOM.L CH.BCRLIN CH.BLIN C.L.BGM C.M.GL C..ML C.OL.M C.O.MLP CR.B.LI CR.LINMO H..BML H.L.BCM L..BMO L.BO.CM L.H.BM LIN.CR.LI M.BC.GL M..BCL M.B.CLO M.BH.CGO M.B.L M.BL.GO M.O.BCGL MO.BCR MO.BCRJUO O.B.CHMLO
X.MOSSa factor with levels -9999 HSDC HSDR HSSC HSSR PS PSDC PSDR PSRD PSSC
X.TOPa factor with levels -9999 D10 D6 D7 M10 M4 M5 M6 M7 M8
AoMEANa numeric vector
X.AoRANGEa factor with levels 0.1_1.0 0_2 0.2_2.5 0.2_4.0 0,5_2 0,5_3 0.5_4.0 0.5_5.0 1.0_3.0 1_2 1_3 1_4 1_5 1.5_3.5 1,5_5 1_6 2_ 2.0_5.0 2.0_6.0 2.0_7.0 2_3 2_4 2_5 2_6 2_7 3.0_8.0 3_12 3_5 3_6 4_12 4_6 4_8 5_ 5_10 .5_4 -9999
HUMNOa numeric vector
HUMTHIa numeric vector
X.C_PARa factor with levels FLUV FLUVG TILL TILLSAP TILL&SAP
X.C_graina numeric vector
X.COLAa numeric vector
X.COLEa numeric vector
LOWDEa numeric vector
X.COLBa numeric vector
LOWDBa numeric vector
X.COLCa numeric vector
TOPCa numeric vector
X.WEATHa factor with levels DRY MIX RAIN
TEMPa numeric vector
CATLEV0a numeric vector
CATLEV1a numeric vector
CATLEV2a numeric vector
LITOa numeric vector
F1_Ag.1a numeric vector
F1_Ag.2a numeric vector
F2_Ag.1a numeric vector
F1_Al2O3.1a numeric vector
F1_Al2O3.2a numeric vector
F2_Al2O3.1a numeric vector
F1_Au_INAA.1a numeric vector
F1_Au_INAA.2a numeric vector
F2_Au_INAA.1a numeric vector
F1_Ba_INAA.1a numeric vector
F1_Ba_INAA.2a numeric vector
F2_Ba_INAA.1a numeric vector
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
Kola Project (1993-1998)
Reimann C, ?yr?s M, Chekushin V, Bogatyrev I, Boyd R, Caritat P de, Dutter R, Finne TE, Halleraker JH, J?ger ?, Kashulina G, Lehto O, Niskavaara H, Pavlov V, R?is?nen ML, Strand T, Volden T. Environmental Geochemical Atlas of the Central Barents Region. NGU-GTK-CKE Special Publication, Geological Survey of Norway, Trondheim, Norway, 1998.
data(CHorFieldDUP) str(CHorFieldDUP)data(CHorFieldDUP) str(CHorFieldDUP)
The Kola Data were collected in the Kola Project (1993-1998, Geological Surveys of Finland (GTK) and Norway (NGU) and Central Kola Expedition (CKE), Russia). More than 600 samples in five different layers were analysed, this dataset contains the C-horizon.
data(chorizon)data(chorizon)
A data frame with 606 observations on the following 111 variables.
IDa numeric vector
XCOOa numeric vector
YCOOa numeric vector
ELEVa numeric vector
COUNa factor with levels FIN NOR RUS
ASPa factor with levels E FLAT N NE NW NW S SE SW W
TOPCa numeric vector
LITOa numeric vector
Aga numeric vector
Ag_INAAa numeric vector
Ala numeric vector
Al_XRFa numeric vector
Al2O3a numeric vector
Asa numeric vector
As_INAAa numeric vector
Aua numeric vector
Au_INAAa numeric vector
Ba numeric vector
Baa numeric vector
Ba_INAAa numeric vector
Bea numeric vector
Bia numeric vector
Br_ICa numeric vector
Br_INAAa numeric vector
Caa numeric vector
Ca_INAAa numeric vector
Ca_XRFa numeric vector
CaOa numeric vector
Cda numeric vector
Ce_INAAa numeric vector
Cl_ICa numeric vector
Coa numeric vector
Co_INAAa numeric vector
Cra numeric vector
Cr_INAAa numeric vector
Cs_INAAa numeric vector
Cua numeric vector
ECa numeric vector
Eu_INAAa numeric vector
F_ICa numeric vector
Fea numeric vector
Fe_INAAa numeric vector
Fe_XRFa numeric vector
Fe2O3a numeric vector
Hf_INAAa numeric vector
Hga numeric vector
Hg_INAAa numeric vector
Ir_INAAa numeric vector
Ka numeric vector
K_XRFa numeric vector
K2Oa numeric vector
Laa numeric vector
La_INAAa numeric vector
Lia numeric vector
LOIa numeric vector
Lu_INAAa numeric vector
Mga numeric vector
Mg_XRFa numeric vector
MgOa numeric vector
Mna numeric vector
Mn_XRFa numeric vector
MnOa numeric vector
Moa numeric vector
Mo_INAAa numeric vector
Naa numeric vector
Na_INAAa numeric vector
Na_XRFa numeric vector
Na2Oa numeric vector
Nd_INAAa numeric vector
Nia numeric vector
Ni_INAAa numeric vector
NO3_ICa numeric vector
Pa numeric vector
P_XRFa numeric vector
P2O5a numeric vector
Pba numeric vector
Pda numeric vector
pHa numeric vector
PO4_ICa numeric vector
Pta numeric vector
Rba numeric vector
Sa numeric vector
Sba numeric vector
Sb_INAAa numeric vector
Sca numeric vector
Sc_INAAa numeric vector
Sea numeric vector
Se_INAAa numeric vector
Sia numeric vector
Si_XRFa numeric vector
SiO2a numeric vector
Sm_INAAa numeric vector
Sn_INAAa numeric vector
SO4_ICa numeric vector
Sra numeric vector
Sr_INAAa numeric vector
Ta_INAAa numeric vector
Tb_INAAa numeric vector
Tea numeric vector
Tha numeric vector
Th_INAAa numeric vector
Tia numeric vector
Ti_XRFa numeric vector
TiO2a numeric vector
U_INAAa numeric vector
Va numeric vector
W_INAAa numeric vector
Ya numeric vector
Yb_INAAa numeric vector
Zna numeric vector
Zn_INAAa numeric vector
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
Kola Project (1993-1998)
Reimann C, ?yr?s M, Chekushin V, Bogatyrev I, Boyd R, Caritat P de, Dutter R, Finne TE, Halleraker JH, J?ger ?, Kashulina G, Lehto O, Niskavaara H, Pavlov V, R?is?nen ML, Strand T, Volden T. Environmental Geochemical Atlas of the Central Barents Region. NGU-GTK-CKE Special Publication, Geological Survey of Norway, Trondheim, Norway, 1998.
data(chorizon) str(chorizon)data(chorizon) str(chorizon)
This is needed for quality control.
data(CHorSTANDARD)data(CHorSTANDARD)
A data frame with 52 observations on the following 95 variables.
X.Loca numeric vector
Aga numeric vector
Ag_INAAa numeric vector
Ala numeric vector
Al2O3a numeric vector
Asa numeric vector
As_INAAa numeric vector
Au_INAAa numeric vector
Ba numeric vector
Baa numeric vector
Ba_INAAa numeric vector
Bea numeric vector
Bia numeric vector
Bra numeric vector
Br_INAAa numeric vector
Caa numeric vector
Ca_INAAa numeric vector
CaOa numeric vector
Cda numeric vector
Ce_INAAa numeric vector
Cl.a numeric vector
Coa numeric vector
Co_INAAa numeric vector
Conda numeric vector
Cra numeric vector
Cr_INAAa numeric vector
Cs_INAAa numeric vector
Cua numeric vector
Eu_INAAa numeric vector
F.a numeric vector
F_ionselecta numeric vector
Fea numeric vector
Fe_INAAa numeric vector
Fe2O3a numeric vector
Hf_INAAa numeric vector
Hga numeric vector
Hg_INAAa numeric vector
Ir_INAAa numeric vector
Ka numeric vector
K2Oa numeric vector
Laa numeric vector
La_INAAa numeric vector
Lia numeric vector
LOIa numeric vector
Lu_INAAa numeric vector
Mass_INAAa numeric vector
Mga numeric vector
MgOa numeric vector
Mna numeric vector
MnOa numeric vector
Moa numeric vector
Mo_INAAa numeric vector
Naa numeric vector
Na_INAAa numeric vector
Na2Oa numeric vector
Nd_INAAa numeric vector
Nia numeric vector
Ni_INAAa numeric vector
NO2.a numeric vector
NO3.a numeric vector
Pa numeric vector
P2O5a numeric vector
Pba numeric vector
pHa numeric vector
PO4...a numeric vector
Rba numeric vector
Sa numeric vector
Sba numeric vector
Sb_INAAa numeric vector
Sca numeric vector
Sc_INAAa numeric vector
Sea numeric vector
Se_INAAa numeric vector
Sia numeric vector
SiO2a numeric vector
Sm_INAAa numeric vector
Sn_INAAa numeric vector
SO4..a numeric vector
Sra numeric vector
Sr_INAAa numeric vector
Suma numeric vector
Ta_INAAa numeric vector
Tb_INAAa numeric vector
Tea numeric vector
Tha numeric vector
Th_INAAa numeric vector
Tia numeric vector
TiO2a numeric vector
U_INAAa numeric vector
Va numeric vector
W_INAAa numeric vector
Ya numeric vector
Yb_INAAa numeric vector
Zna numeric vector
Zn_INAAa numeric vector
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
Kola Project (1993-1998)
Reimann C, ?yr?s M, Chekushin V, Bogatyrev I, Boyd R, Caritat P de, Dutter R, Finne TE, Halleraker JH, J?ger ?, Kashulina G, Lehto O, Niskavaara H, Pavlov V, R?is?nen ML, Strand T, Volden T. Environmental Geochemical Atlas of the Central Barents Region. NGU-GTK-CKE Special Publication, Geological Survey of Norway, Trondheim, Norway, 1998.
data(CHorSTANDARD) str(CHorSTANDARD)data(CHorSTANDARD) str(CHorSTANDARD)
Displays a concentration-area plot (see also concareaExampleKola). This function is preferable since it can be applied to non-Kola data!
concarea(x, y, z, zname = deparse(substitute(z)), caname = deparse(substitute(z)), borders=NULL, logx = FALSE, ifjit = FALSE, ifrev = FALSE, ngrid = 100, ncp = 0, xlim = NULL, xcoord = "Easting", ycoord = "Northing", ifbw = FALSE, x.logfinetick = c(2, 5, 10), y.logfinetick = c(2, 5, 10))concarea(x, y, z, zname = deparse(substitute(z)), caname = deparse(substitute(z)), borders=NULL, logx = FALSE, ifjit = FALSE, ifrev = FALSE, ngrid = 100, ncp = 0, xlim = NULL, xcoord = "Easting", ycoord = "Northing", ifbw = FALSE, x.logfinetick = c(2, 5, 10), y.logfinetick = c(2, 5, 10))
x |
name of the x-axis spatial coordinate, the eastings |
y |
name of the y-axis spatial coordinate, the northings |
z |
name of the variable to be processed and plotted |
zname |
a title for the x-axes of the qp-plot and concentration area plot. |
caname |
a title for the image of interpolated data. |
borders |
either NULL or character string with the name of the list with list elements x and y for x- and y-coordinates of map borders |
logx |
if it is required to make a logarithmis data transformation for the interpolation |
ifrev |
if FALSE the empirical function ist plotted from highest value to lowest |
ngrid |
default value is 100 |
xlim |
the range for the x-axis |
xcoord |
a title for the x-axis, defaults to "Easting" |
ycoord |
a title for the y-axis, defaults to "Northing" |
ifbw |
if the plot is drawn in black and white |
x.logfinetick |
how fine are the tick marks on log-scale on x-axis |
y.logfinetick |
how fine are the tick marks on log-scale on y-axis |
ifjit |
default value is FALSE |
ncp |
default value is 0 |
The function assumes that the area is proportional to the count of grid points. To be a reasonable model the data points should be 'evenly' spread over the plane. The interpolated grid size ist computed as (max(x) - min(x))/ngrid, with a default value of 100 for ngrid. Akima's interpolation function is used to obtain a linear interpolation between the spatial data values.
The concentration area plot, in both directions, is created.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(ohorizon) data(kola.background) data(bordersKola) Cu=ohorizon[,"Cu"] X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] op <- par(mfrow=c(1,2),mar=c(4,4,2,2)) concarea(X,Y,Cu,log=TRUE,zname="Cu in O-horizon [mg/kg]",borders="bordersKola", ifrev=FALSE, x.logfinetick=c(2,5,10),y.logfinetick=c(10)) par(op)data(ohorizon) data(kola.background) data(bordersKola) Cu=ohorizon[,"Cu"] X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] op <- par(mfrow=c(1,2),mar=c(4,4,2,2)) concarea(X,Y,Cu,log=TRUE,zname="Cu in O-horizon [mg/kg]",borders="bordersKola", ifrev=FALSE, x.logfinetick=c(2,5,10),y.logfinetick=c(10)) par(op)
Displays a concentration area plot example for the Kola data. This procedure ist useful for determining if mulitple populations that are spatially dependent are present in a data set. For a more general function see concarea.
concareaExampleKola(x, y, z, zname = deparse(substitute(z)), caname = deparse(substitute(z)), borders="bordersKola", logx = FALSE, ifjit = FALSE, ifrev = FALSE, ngrid = 100, ncp = 0, xlim = NULL, xcoord = "Easting", ycoord = "Northing", ifbw = FALSE, x.logfinetick = c(2, 5, 10), y.logfinetick = c(2, 5, 10))concareaExampleKola(x, y, z, zname = deparse(substitute(z)), caname = deparse(substitute(z)), borders="bordersKola", logx = FALSE, ifjit = FALSE, ifrev = FALSE, ngrid = 100, ncp = 0, xlim = NULL, xcoord = "Easting", ycoord = "Northing", ifbw = FALSE, x.logfinetick = c(2, 5, 10), y.logfinetick = c(2, 5, 10))
x |
name of the x-axis spatial coordinate, the eastings |
y |
name of the y-axis spatial coordinate, the northings |
z |
name of the variable to be processed and plotted |
zname |
a title for the x-axes of the qp-plot and concentration area plot. |
caname |
a title for the image of interpolated data. |
borders |
either NULL or character string with the name of the list with list elements x and y for x- and y-coordinates of map borders |
logx |
if it is required to make a logarithmis data transformation for the interpolation |
ifrev |
if FALSE the empirical function ist plotted from highest value to lowest |
ngrid |
default value is 100 |
xlim |
the range for the x-axis |
xcoord |
a title for the x-axis, defaults to "Easting" |
ycoord |
a title for the y-axis, defaults to "Northing" |
ifbw |
if the plot is drawn in black and white |
x.logfinetick |
how fine are the tick marks on log-scale on x-axis |
y.logfinetick |
how fine are the tick marks on log-scale on y-axis |
ifjit |
default value is FALSE |
ncp |
default value is 0 |
The function assumes that the area is proportional to the count of grid points. To be a reasonable model the data points should be 'evenly' spread over the plane. The interpolated grid size ist computed as (max(x) - min(x))/ngrid, with a default value of 100 for ngrid. Akima's interpolation function is used to obtain a linear interpolation between the spatial data values.
An example concentration area plot for Kola is created.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(ohorizon) data(kola.background) data(bordersKola) Cu=ohorizon[,"Cu"] X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] op <- par(mfrow=c(2,2),mar=c(1.5,1.5,1.5,1.5)) concareaExampleKola(X,Y,Cu,log=TRUE,zname="Cu in O-horizon [mg/kg]", x.logfinetick=c(2,5,10),y.logfinetick=c(10)) par(op)data(ohorizon) data(kola.background) data(bordersKola) Cu=ohorizon[,"Cu"] X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] op <- par(mfrow=c(2,2),mar=c(1.5,1.5,1.5,1.5)) concareaExampleKola(X,Y,Cu,log=TRUE,zname="Cu in O-horizon [mg/kg]", x.logfinetick=c(2,5,10),y.logfinetick=c(10)) par(op)
Computes correlation matrix of x with method "pearson", "kendall" or "spearman". This function also prints the matrix with the significance levels.
cor.sign(x, method = c("pearson", "kendall", "spearman"))cor.sign(x, method = c("pearson", "kendall", "spearman"))
x |
the data |
method |
the method used |
This function estimate the association between paired samples an compute a test of the value being zero. All measures of association are in the range [-1,1] with 0 indicating no association.
cor |
Correlation matrix |
p.value |
p-value of the test statistic |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(chorizon) x=chorizon[,c("Ca","Cu","Mg","Na","P","Sr","Zn")] cor.sign(log10(x),method="spearman")data(chorizon) x=chorizon[,c("Ca","Cu","Mg","Na","P","Sr","Zn")] cor.sign(log10(x),method="spearman")
This function compares two correlation matrices numerically and graphically.
CorCompare(cor1, cor2, labels1, labels2, method1, method2, ndigits = 4, lty1 = 1, lty2 = 2, col1 = 1, col2 = 2, lwd1 = 1.1, lwd2 = 1.1, cex.label = 1.1, cex.legend = 1.2, lwd.legend = 1.2, cex.cor = 1, ...)CorCompare(cor1, cor2, labels1, labels2, method1, method2, ndigits = 4, lty1 = 1, lty2 = 2, col1 = 1, col2 = 2, lwd1 = 1.1, lwd2 = 1.1, cex.label = 1.1, cex.legend = 1.2, lwd.legend = 1.2, cex.cor = 1, ...)
cor1, cor2
|
two correlation matrices based on different estimation methods |
labels1, labels2
|
labels for the two estimation methods |
method1, method2
|
description of the estimation methods |
ndigits |
number of digits to be used for plotting the numbers |
lty1, lty2, col1, col2, lwd1, lwd2, cex.label, cex.cor
|
other graphics parameters |
cex.legend, lwd.legend
|
graphical parameters for the legend |
... |
further graphical parameters for the ellipses |
The ellipses are plotted with the function do.ellipses. Therefore the radius is calculated with singular value decomposition.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(chorizon) x=chorizon[,c("Ca","Cu","Mg","Na","P","Sr","Zn")] op <- par(mfrow=c(1,1),mar=c(4,4,2,0)) R=robustbase::covMcd(log10(x),cor=TRUE)$cor P=cor(log10(x)) CorCompare(R,P,labels1=dimnames(x)[[2]],labels2=dimnames(x)[[2]], method1="Robust",method2="Pearson",ndigits=2, cex.label=1.2) par(op)data(chorizon) x=chorizon[,c("Ca","Cu","Mg","Na","P","Sr","Zn")] op <- par(mfrow=c(1,1),mar=c(4,4,2,0)) R=robustbase::covMcd(log10(x),cor=TRUE)$cor P=cor(log10(x)) CorCompare(R,P,labels1=dimnames(x)[[2]],labels2=dimnames(x)[[2]], method1="Robust",method2="Pearson",ndigits=2, cex.label=1.2) par(op)
The correlation matrix for sub-groups of data is computed and displayed in a graphic.
CorGroups(dat, grouping, labels1, labels2, legend, ndigits = 4, method = "pearson", ...)CorGroups(dat, grouping, labels1, labels2, legend, ndigits = 4, method = "pearson", ...)
dat |
data values (probably log10-transformed) |
grouping |
factor with levels for different groups |
labels1, labels2
|
labels for groups |
legend |
plotting legend |
ndigits |
number of digits to be used for plotting the numbers |
method |
correlation method: "pearson", "spearman" or "kendall" |
... |
will not be used in the function |
The corralation is estimated with a non robust method but it is possible to select between the method of Pearson, Spearman and Kendall. The groups must be provided by the user.
Graphic with the different sub-groups.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(chorizon) x=chorizon[,c("Ca","Cu","Mg","Na","P","Sr","Zn")] #definition of the groups lit=chorizon[,"LITO"] litolog=rep(NA, length(lit)) litolog[lit==10] <- 1 litolog[lit==52] <- 2 litolog[lit==81 | lit==82 | lit==83] <- 3 litolog[lit==7] <- 4 litolog <- litolog[!is.na(litolog)] litolog <- factor(litolog, labels=c("AB","PG","AR","LPS")) op <- par(mfrow=c(1,1),mar=c(0.1,0.1,0.1,0.1)) CorGroups(log10(x), grouping=litolog, labels1=dimnames(x)[[2]],labels2=dimnames(x)[[2]], legend=c("Caledonian Sediments","Basalts","Alkaline Rocks","Granites"),ndigits=2) par(op)data(chorizon) x=chorizon[,c("Ca","Cu","Mg","Na","P","Sr","Zn")] #definition of the groups lit=chorizon[,"LITO"] litolog=rep(NA, length(lit)) litolog[lit==10] <- 1 litolog[lit==52] <- 2 litolog[lit==81 | lit==82 | lit==83] <- 3 litolog[lit==7] <- 4 litolog <- litolog[!is.na(litolog)] litolog <- factor(litolog, labels=c("AB","PG","AR","LPS")) op <- par(mfrow=c(1,1),mar=c(0.1,0.1,0.1,0.1)) CorGroups(log10(x), grouping=litolog, labels1=dimnames(x)[[2]],labels2=dimnames(x)[[2]], legend=c("Caledonian Sediments","Basalts","Alkaline Rocks","Granites"),ndigits=2) par(op)
This function plots ellipses according to a covariance matrix
do.ellipses(acov, pos, ...)do.ellipses(acov, pos, ...)
acov |
the given covariance matrix |
pos |
the location of the ellipse |
... |
further graphical parameter for the ellipses |
The correlation matrix of the given covariance is computed and the resulting ellipse is plotted. The radi is computed with the singular value decomposition and the cos/sin is calculated for 100 different degrees.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
#internal function, used in CorCompare#internal function, used in CorCompare
This function plots a histogram of the data. There is also the choice to add the density, a boxplot and a scatterplot to the histogram.
edaplot(data,scatter=TRUE,box=TRUE, P.plot=TRUE, D.plot=TRUE, P.main=paste("Histogram of",deparse(substitute(data))), P.sub=NULL, P.xlab=deparse(substitute(data)), P.ylab=default, P.ann=par("ann"), P.axes=TRUE, P.frame.plot=P.axes, P.log=FALSE, P.logfine=c(2,5,10), P.xlim=NULL, P.cex.lab=1.4,B.range=1.5, B.notch=FALSE, B.outline=TRUE, B.border=par("fg"), B.col=NULL, B.pch=par("pch"), B.cex=1, B.bg=NA, H.breaks="Sturges", H.freq=TRUE, H.include.lowest=TRUE, H.right=TRUE, H.density=NULL, H.angle=45, H.col=NULL, H.border=NULL, H.labels=FALSE, S.pch=".", S.col=par("col"), S.bg=NA, S.cex=1, D.lwd=1,D.lty=1)edaplot(data,scatter=TRUE,box=TRUE, P.plot=TRUE, D.plot=TRUE, P.main=paste("Histogram of",deparse(substitute(data))), P.sub=NULL, P.xlab=deparse(substitute(data)), P.ylab=default, P.ann=par("ann"), P.axes=TRUE, P.frame.plot=P.axes, P.log=FALSE, P.logfine=c(2,5,10), P.xlim=NULL, P.cex.lab=1.4,B.range=1.5, B.notch=FALSE, B.outline=TRUE, B.border=par("fg"), B.col=NULL, B.pch=par("pch"), B.cex=1, B.bg=NA, H.breaks="Sturges", H.freq=TRUE, H.include.lowest=TRUE, H.right=TRUE, H.density=NULL, H.angle=45, H.col=NULL, H.border=NULL, H.labels=FALSE, S.pch=".", S.col=par("col"), S.bg=NA, S.cex=1, D.lwd=1,D.lty=1)
data |
data set |
scatter |
if TRUE the scatter plot is added |
box |
if TRUE a boxplot or boxplotlog is added |
P.plot |
if it is plotted or just a list is computed |
D.plot |
if TRUE the density is added |
P.main, P.sub, P.xlab, P.ylab, P.ann
|
graphical parameters for the density, see plot |
P.axes, P.frame.plot
|
plots the y-axis with the ticker |
P.log |
if TRUE the x-axis is in log-scale |
P.logfine |
how fine the tickers are |
P.xlim, P.cex.lab
|
further graphical parameters |
B.range, B.notch, B.outline, B.border, B.col, B.pch, B.cex, B.bg
|
parameters for boxplot and boxplotlog function, see boxplot and boxplotlog |
H.breaks, H.freq, H.include.lowest, H.right, H.density, H.angle, H.col, H.border, H.labels
|
parameters for histogram, see hist |
S.pch, S.col, S.bg, S.cex
|
graphical parameters for the shape of the points, see points |
D.lwd, D.lty
|
parameters for the density |
First the histogram, boxplot/boxplotlog and density is calculate and then the plot is produced. The default is that histogram, boxplot, density trace and scatterplot is made.
H |
results of the histogram |
B |
results of the boxplot |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
plot,boxplot, edaplotlog, hist, points
data(chorizon) Ba=chorizon[,"Ba"] edaplot(Ba,H.freq=FALSE,box=TRUE,H.breaks=30,S.pch=3,S.cex=0.5,D.lwd=1.5,P.log=FALSE, P.main="",P.xlab="Ba [mg/kg]",P.ylab="Density",B.pch=3,B.cex=0.5)data(chorizon) Ba=chorizon[,"Ba"] edaplot(Ba,H.freq=FALSE,box=TRUE,H.breaks=30,S.pch=3,S.cex=0.5,D.lwd=1.5,P.log=FALSE, P.main="",P.xlab="Ba [mg/kg]",P.ylab="Density",B.pch=3,B.cex=0.5)
This function plots a histogram of the data. There is also the choice to add the density, a boxplot and a scatterplot to the histogram.
edaplotlog(data, scatter = TRUE, box = TRUE, P.plot = TRUE, D.plot = TRUE, P.main = paste("Histogram of", deparse(substitute(data))), P.sub = NULL, P.xlab = deparse(substitute(data)), P.ylab = default, P.ann = par("ann"), P.axes = TRUE, P.frame.plot = P.axes, P.log = FALSE, P.logfine = c(2, 5, 10), P.xlim = NULL, P.cex.lab = 1.4, B.range = 1.5, B.notch = FALSE, B.outline = TRUE, B.border = par("fg"), B.col = NULL, B.pch = par("pch"), B.cex = 1, B.bg = NA, B.log = FALSE, H.breaks = "Sturges", H.freq = TRUE, H.include.lowest = TRUE, H.right = TRUE, H.density = NULL, H.angle = 45, H.col = NULL, H.border = NULL, H.labels = FALSE, S.pch = ".", S.col = par("col"), S.bg = NA, S.cex = 1, D.lwd = 1, D.lty = 1)edaplotlog(data, scatter = TRUE, box = TRUE, P.plot = TRUE, D.plot = TRUE, P.main = paste("Histogram of", deparse(substitute(data))), P.sub = NULL, P.xlab = deparse(substitute(data)), P.ylab = default, P.ann = par("ann"), P.axes = TRUE, P.frame.plot = P.axes, P.log = FALSE, P.logfine = c(2, 5, 10), P.xlim = NULL, P.cex.lab = 1.4, B.range = 1.5, B.notch = FALSE, B.outline = TRUE, B.border = par("fg"), B.col = NULL, B.pch = par("pch"), B.cex = 1, B.bg = NA, B.log = FALSE, H.breaks = "Sturges", H.freq = TRUE, H.include.lowest = TRUE, H.right = TRUE, H.density = NULL, H.angle = 45, H.col = NULL, H.border = NULL, H.labels = FALSE, S.pch = ".", S.col = par("col"), S.bg = NA, S.cex = 1, D.lwd = 1, D.lty = 1)
data |
data set |
scatter |
if TRUE the scatter plot is added |
box |
if TRUE a boxplot or boxplotlog is added |
P.plot |
if it is plotted or just a list is computed |
D.plot |
if TRUE the density is added |
P.main, P.sub, P.xlab, P.ylab, P.ann
|
graphical parameters for the density, see plot |
P.axes, P.frame.plot
|
plots the y-axis with the ticker |
P.log |
if TRUE the x-axis is in log-scale |
P.logfine |
how fine the tickers are |
P.xlim, P.cex.lab
|
further graphical parameters |
B.range, B.notch, B.outline, B.border, B.col, B.pch, B.cex, B.bg
|
parameters for boxplot and boxplotlog function, see boxplot and boxplotlog |
B.log |
if TRUE the function boxplotlog is used instead of boxplot |
H.breaks, H.include.lowest, H.right, H.density, H.angle, H.col, H.border, H.labels
|
parameters for histogram, see hist |
H.freq |
uses the number of data points in the range |
S.pch, S.col, S.bg, S.cex
|
graphical parameters for the shape of the points, see points |
D.lwd, D.lty
|
parameters for the density |
First the histogram, boxplot/boxplotlog and density is calculate and then the plot is produced. The default is that histogram, boxplot, density trace and scatterplot is made.
H |
results of the histogram |
B |
results of boxplotlog |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
plot,boxplot, boxplotlog, hist, points
data(chorizon) Ba=chorizon[,"Ba"] edaplotlog(Ba,H.freq=FALSE,box=TRUE,H.breaks=30,S.pch=3,S.cex=0.5,D.lwd=1.5,P.log=FALSE, P.main="",P.xlab="Ba [mg/kg]",P.ylab="Density",B.pch=3,B.cex=0.5,B.log=TRUE)data(chorizon) Ba=chorizon[,"Ba"] edaplotlog(Ba,H.freq=FALSE,box=TRUE,H.breaks=30,S.pch=3,S.cex=0.5,D.lwd=1.5,P.log=FALSE, P.main="",P.xlab="Ba [mg/kg]",P.ylab="Density",B.pch=3,B.cex=0.5,B.log=TRUE)
Internal function for pfa.
factanal.fit.principal(cmat, factors, p = ncol(cmat), start = NULL, iter.max = 10, unique.tol = 1e-04)factanal.fit.principal(cmat, factors, p = ncol(cmat), start = NULL, iter.max = 10, unique.tol = 1e-04)
cmat |
provided correlation matrix |
factors |
number of factors |
p |
number of observations |
start |
vector of start values |
iter.max |
maximum number of iteration used to calculate the common factor |
unique.tol |
the tolerance for a deviation of the maximum (in each row, without the diag) value of the given correlation matrix to the new calculated value |
loadings |
A matrix of loadings, one column for each factor. The factors are ordered in decreasing order of sums of squares of loadings. |
uniquness |
uniquness |
correlation |
correlation matrix |
criteria |
The results of the optimization: the value of the negativ log-likelihood and information of the iterations used. |
factors |
the factors |
dof |
degrees of freedom |
method |
"principal" |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
Coordinates of the Kola background. Seperate polygons for the project boundary, borders, lakes and coast are provided.
data(kola.background)data(kola.background)
The format is: List of 4 $ boundary:‘data.frame’: 50 obs. of 2 variables: ..$ V1: num [1:50] 388650 388160 386587 384035 383029 ... ..$ V2: num [1:50] 7892400 7881248 7847303 7790797 7769214 ... $ coast :‘data.frame’: 6259 obs. of 2 variables: ..$ V1: num [1:6259] 438431 439102 439102 439643 439643 ... ..$ V2: num [1:6259] 7895619 7896495 7896495 7895800 7895542 ... $ borders :‘data.frame’: 504 obs. of 2 variables: ..$ V1: num [1:504] 417575 417704 418890 420308 422731 ... ..$ V2: num [1:504] 7612984 7612984 7613293 7614530 7615972 ... $ lakes :‘data.frame’: 6003 obs. of 2 variables: ..$ V1: num [1:6003] 547972 546915 NA 547972 547172 ... ..$ V2: num [1:6003] 7815109 7815599 NA 7815109 7813873 ...
Is used by plotbg()
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
Kola Project (1993-1998)
Reimann C, Ayras M, Chekushin V, Bogatyrev I, Boyd R, Caritat P de, Dutter R, Finne TE, Halleraker JH, Jager O, Kashulina G, Lehto O, Niskavaara H, Pavlov V, Raisanen ML, Strand T, Volden T. Environmental Geochemical Atlas of the Central Barents Region. NGU-GTK-CKE Special Publication, Geological Survey of Norway, Trondheim, Norway, 1998.
data(kola.background) plotbg()data(kola.background) plotbg()
Plots Krige maps and Legend based on continuous or percentile scale.
KrigeLegend(X, Y, z, resol = 100, vario, type = "percentile", whichcol = "gray", qutiles = c(0, 0.05, 0.25, 0.5, 0.75, 0.9, 0.95, 1),borders=NULL, leg.xpos.min = 780000, leg.xpos.max = 8e+05, leg.ypos.min = 7760000, leg.ypos.max = 7870000, leg.title = "mg/kg", leg.title.cex = 0.7, leg.numb.cex = 0.7, leg.round = 2, leg.numb.xshift = 70000, leg.perc.xshift = 40000, leg.perc.yshift = 20000, tit.xshift = 35000)KrigeLegend(X, Y, z, resol = 100, vario, type = "percentile", whichcol = "gray", qutiles = c(0, 0.05, 0.25, 0.5, 0.75, 0.9, 0.95, 1),borders=NULL, leg.xpos.min = 780000, leg.xpos.max = 8e+05, leg.ypos.min = 7760000, leg.ypos.max = 7870000, leg.title = "mg/kg", leg.title.cex = 0.7, leg.numb.cex = 0.7, leg.round = 2, leg.numb.xshift = 70000, leg.perc.xshift = 40000, leg.perc.yshift = 20000, tit.xshift = 35000)
X |
X-coordinates |
Y |
Y-coordinates |
z |
values on the coordinates |
resol |
resolution of blocks for Kriging |
vario |
variogram model |
type |
"percentile" for percentile legend, "contin" for continous grey-scale or colour map |
whichcol |
type of colour scheme to use: "gray", "rainbow", "rainbow.trunc", "rainbow.inv", "terrain", "topo" |
qutiles |
considered quantiles if type="percentile" is used |
borders |
either NULL or character string with the name of the list with list elements x and y for x- and y-coordinates of map borders |
leg.xpos.min |
minimum value of x-position of the legend |
leg.xpos.max |
maximum value of x-position of the legend |
leg.ypos.min |
minimum value of y-position of the legend |
leg.ypos.max |
maximum value of y-position of the legend |
leg.title |
title for legend |
leg.title.cex |
cex for legend title |
leg.numb.cex |
cex for legend number |
leg.round |
round legend to specified digits "pretty" |
leg.numb.xshift |
x-shift of numbers in legend relative to leg.xpos.max |
leg.perc.xshift |
x-shift of "Percentile" in legend relative to leg.xpos.min |
leg.perc.yshift |
y-shift of numbers in legend relative to leg.ypos.max |
tit.xshift |
x-shift of title in legend relative to leg.xpos.max |
Based on a variogram model a interpolation of the spatial data is computed. The variogram has to be provided by the user and based on this model the spatial prediction is made. To distinguish between different values every predicted value is plotted in his own scale of the choosen colour.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(chorizon) data(kola.background) X=chorizon[,"XCOO"] Y=chorizon[,"YCOO"] #el=chorizon[,"As"] #vario.b <- variog(coords=cbind(X,Y), data=el, lambda=0, max.dist=300000) #data(res.eyefit.As_C_m) #need the data #v5=variofit(vario.b,res.eyefit.As_C_m,cov.model="spherical",max.dist=300000) plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n") # to inclrease the resolution, set e.g. resol=100 #data(bordersKola) # x and y coordinates of project boundary #KrigeLegend(X,Y,el,resol=25,vario=v5,type="percentile",whichcol="gray", # qutiles=c(0,0.05,0.25,0.50,0.75,0.90,0.95,1),borders="bordersKola", # leg.xpos.min=7.8e5,leg.xpos.max=8.0e5,leg.ypos.min=77.6e5,leg.ypos.max=78.7e5, # leg.title="mg/kg", leg.title.cex=0.7, leg.numb.cex=0.7, leg.round=2, # leg.numb.xshift=0.7e5,leg.perc.xshift=0.4e5,leg.perc.yshift=0.2e5,tit.xshift=0.35e5) # #plotbg(map.col=c("gray","gray","gray","gray"),map.lwd=c(1,1,1,1),add.plot=TRUE)data(chorizon) data(kola.background) X=chorizon[,"XCOO"] Y=chorizon[,"YCOO"] #el=chorizon[,"As"] #vario.b <- variog(coords=cbind(X,Y), data=el, lambda=0, max.dist=300000) #data(res.eyefit.As_C_m) #need the data #v5=variofit(vario.b,res.eyefit.As_C_m,cov.model="spherical",max.dist=300000) plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n") # to inclrease the resolution, set e.g. resol=100 #data(bordersKola) # x and y coordinates of project boundary #KrigeLegend(X,Y,el,resol=25,vario=v5,type="percentile",whichcol="gray", # qutiles=c(0,0.05,0.25,0.50,0.75,0.90,0.95,1),borders="bordersKola", # leg.xpos.min=7.8e5,leg.xpos.max=8.0e5,leg.ypos.min=77.6e5,leg.ypos.max=78.7e5, # leg.title="mg/kg", leg.title.cex=0.7, leg.numb.cex=0.7, leg.round=2, # leg.numb.xshift=0.7e5,leg.perc.xshift=0.4e5,leg.perc.yshift=0.2e5,tit.xshift=0.35e5) # #plotbg(map.col=c("gray","gray","gray","gray"),map.lwd=c(1,1,1,1),add.plot=TRUE)
Makes a Reimann-plot of a loadings matrix.
loadplot(fa.object, titlepl = "Factor Analysis", crit = 0.3, length.varnames = 2)loadplot(fa.object, titlepl = "Factor Analysis", crit = 0.3, length.varnames = 2)
fa.object |
the output of factor analysis class |
titlepl |
the title of the plot |
crit |
all loadings smaller than crit will be ignored in the plot |
length.varnames |
number of letters for abbreviating the variable names in the plot |
Plot of the loadings of a FA therefore a object of factor analysis class must be provided.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(moss) var=c("Ag","Al","As","B","Ba","Bi","Ca","Cd","Co","Cr","Cu","Fe","Hg","K","Mg","Mn","Mo", "Na","Ni","P","Pb","Rb","S","Sb","Si","Sr","Th","Tl","U","V","Zn") x=log10(moss[,var]) x.mcd=robustbase::covMcd(x,cor=TRUE) x.rsc=scale(x,x.mcd$cent,sqrt(diag(x.mcd$cov))) res5=pfa(x.rsc,factors=2,covmat=x.mcd,scores="regression",rotation="varimax", maxit=0,start=rep(0,ncol(x.rsc))) loadplot(res5,titlepl="Robust FA (log-transformed)", crit=0.3)data(moss) var=c("Ag","Al","As","B","Ba","Bi","Ca","Cd","Co","Cr","Cu","Fe","Hg","K","Mg","Mn","Mo", "Na","Ni","P","Pb","Rb","S","Sb","Si","Sr","Th","Tl","U","V","Zn") x=log10(moss[,var]) x.mcd=robustbase::covMcd(x,cor=TRUE) x.rsc=scale(x,x.mcd$cent,sqrt(diag(x.mcd$cov))) res5=pfa(x.rsc,factors=2,covmat=x.mcd,scores="regression",rotation="varimax", maxit=0,start=rep(0,ncol(x.rsc))) loadplot(res5,titlepl="Robust FA (log-transformed)", crit=0.3)
This gives x- and y-coordinates with the boundary of the area around Monchegorsk.
data(monch)data(monch)
The format is: List of 2 $ x: num [1:32] 710957 734664 754666 770223 779113 ... $ y: num [1:32] 7473981 7473143 7474818 7483191 7488215 ...
This object can be used to select samples from the Kola data from the region around Monchegorsk.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(monch) data(kola.background) plotbg() lines(monch$x,monch$y,col="red")data(monch) data(kola.background) plotbg() lines(monch$x,monch$y,col="red")
The Kola Data were collected in the Kola Project (1993-1998, Geological Surveys of Finland (GTK) and Norway (NGU) and Central Kola Expedition (CKE), Russia). More than 600 samples in five different layers were analysed, this dataset contains the moss layer.
data(moss)data(moss)
A data frame with 594 observations on the following 58 variables.
IDa numeric vector
XCOOa numeric vector
YCOOa numeric vector
ELEVa numeric vector
COUNa factor with levels FIN NOR RUS
ASPa factor with levels E FLAT N NE NW NW S SE SW W
GENLANa factor with levels DEEPVAL FLA PLAIN FLAT HIMO LOWMO PLAIN PLAT RIDGE SLOPE
TOPOa factor with levels BRUP BRUPLOW BRUPSTEE CONC CONCFLAT CONCLOW CONCMED CONCRUG CONCTERR CONV CONVLO CONVLOW CONVMED CONVTER FLAT FLATLOW FLATRUG FLATTER FLATTERR LOBRRUG LOW LOWBR LOWBRFLAT LOWBRLO LOWBRLOW LOWBRMED RUG RUGLOW TER TERLOW TERR TERRLOW TOHIFLAT TOP TOPFLAT TOPHILO TOPLOW TOPTER TOPUPBR UPBR UPBRFLAT UPBRLOW UPBRMED UPBRTER UPBRTERR UPTER
GROUNDVEGa factor with levels BLUEBERRY CARLIN_HEATHER EMPETRUM GRASS LICHEN MOSS SHRUBS WHITE_LICHEN
TREELAYa factor with levels BIPI BIPISPR BIRCH BIRCHdense BISPR BISPRPI MIX PIBI PIBISPR PINE PISPR PISPRBI SHRUBS SPARCEBI SPARCEPI SPRBI SPRBIPI SPRPI SPRPIBI SPRUCE WILLOW
VEG_ZONEa factor with levels BOREAL_FOREST DWARF_SHRUB_TUNDRA FOREST_TUNDRA SHRUB_TUNDRA TUNDRA
Datea numeric vector
SAMPa factor with levels ALL ATMLRMA CRGKPCTF CRJHOJTV CRJHPC CRJHTF CROJTV CRPCTF CRPCTV CRTF DRMLRKK DRMRLKK GKJHOJ GKJHTV GKOJPCTV GKOJTF GKOJTV GKPCTF HARR JA JAMAMRL JAMLRMA JAMLRRR JARKP JARP JARPMA JARPMLR JARR JARRMLR JCPCTF JHGKTV JHOJGK JHOJTV JHPCTF JHRBTV Katanaev MAKKVG MARP MARPMLR MARPMRL MAVG MLR MLRJA MLRJARP MLRJARR MLRJSRR MLRMADR MLRMAJA MLRMARP MLRMAVG MLRM?VG MLRRPJA MLRRPMA MRLMAJA OJGKTV OJTF Pavlov RPAV RPEM RPMA RPMLRJA RPMLRMA RPVM Semenov Smirnov TFOJ VGHNMA VGMA VGMAHN VGMARS VGMASR VGRSMA VMRP VMRPMA
SPECIESa factor with levels HSDC HSDR HSRC HSSC HSSR PS PSDC PSDR PSRC PSRD PSSC PSSR SFDR
LITOa numeric vector
C_PARa factor with levels BEDR FLUV FLUVG MAR SAP SEA STRAT TILL TILLSA TILLSAP TILL&SAP
TOPCa numeric vector
WEATHa factor with levels DRY DRY MIX MIX RAIN SNOW
TEMPa numeric vector
Aga numeric vector
Ala numeric vector
Asa numeric vector
Aua numeric vector
Ba numeric vector
Baa numeric vector
Bea numeric vector
Bia numeric vector
Caa numeric vector
Cda numeric vector
Coa numeric vector
Cra numeric vector
Cua numeric vector
Fea numeric vector
Hga numeric vector
Ka numeric vector
Laa numeric vector
Mga numeric vector
Mna numeric vector
Moa numeric vector
Naa numeric vector
Nia numeric vector
Pa numeric vector
Pba numeric vector
Pda numeric vector
Pta numeric vector
Rba numeric vector
Sa numeric vector
Sba numeric vector
Sca numeric vector
Sea numeric vector
Sia numeric vector
Sra numeric vector
Tha numeric vector
Tla numeric vector
Ua numeric vector
Va numeric vector
Ya numeric vector
Zna numeric vector
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
Kola Project (1993-1998)
Reimann C, ?yr?s M, Chekushin V, Bogatyrev I, Boyd R, Caritat P de, Dutter R, Finne TE, Halleraker JH, J?ger ?, Kashulina G, Lehto O, Niskavaara H, Pavlov V, R?is?nen ML, Strand T, Volden T. Environmental Geochemical Atlas of the Central Barents Region. NGU-GTK-CKE Special Publication, Geological Survey of Norway, Trondheim, Norway, 1998.
data(moss) str(moss)data(moss) str(moss)
This gives x- and y-coordinates with the boundary of the area around Nikel-Zapoljarnij.
data(nizap)data(nizap)
The format is: List of 2 $ x: num [1:36] 699104 693918 681324 662062 645023 ... $ y: num [1:36] 7739416 7746115 7751139 7756163 7757000 ...
This object can be used to select samples from the Kola data from the region around Nikel-Zapoljarnij.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(nizap) data(kola.background) plotbg() lines(nizap$x,nizap$y,col="red")data(nizap) data(kola.background) plotbg() lines(nizap$x,nizap$y,col="red")
Add a North Arrow to a map.
Northarrow(Xbottom, Ybottom, Xtop, Ytop, Xtext, Ytext, Alength, Aangle, Alwd, Tcex)Northarrow(Xbottom, Ybottom, Xtop, Ytop, Xtext, Ytext, Alength, Aangle, Alwd, Tcex)
Xbottom |
x coordinate of the first point |
Ybottom |
y coordinate of the first point |
Xtop |
x coordinate of the second point |
Ytop |
y coordinate of the second point |
Xtext |
x coordinate of the label |
Ytext |
y coordinate of the label |
Alength |
length of the edges of the arrow head (in inches) |
Aangle |
angle from the shaft of the arrow to the edge of the arrow head |
Alwd |
The line width, a positive number |
Tcex |
numeric character expansion factor |
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
plot.new() Northarrow(0.5,0,0.5,1,0.5,0.5,Alength=0.15,Aangle=15,Alwd=2,Tcex=2)plot.new() Northarrow(0.5,0,0.5,1,0.5,0.5,Alength=0.15,Aangle=15,Alwd=2,Tcex=2)
The Kola Data were collected in the Kola Project (1993-1998, Geological Surveys of Finland (GTK) and Norway (NGU) and Central Kola Expedition (CKE), Russia). More than 600 samples in five different layers were analysed, this dataset contains the O-horizon.
data(ohorizon)data(ohorizon)
A data frame with 617 observations on the following 85 variables.
IDa numeric vector
XCOOa numeric vector
YCOOa numeric vector
ELEVa numeric vector
COUNa factor with levels FIN NOR RUS
X.ASPa factor with levels -9999 E FLAT N NE NW NW S SE SW W
AoMEANa numeric vector
HUMNOa numeric vector
HUMTHIa numeric vector
GROUNDVEGa factor with levels BLUEBERRY CARLIN_HEATHER EMPETRUM GRASS LICHEN MOSS SHRUBS WHITE_LICHEN
TREELAYa factor with levels BIPI BIPISPR BIRCH BIRCHdense BISPR BISPRPI MIX PIBI PIBISPR PINE PISPR PISPRBI SHRUBS SPARCEBI SPARCEPI SPRBI SPRBIPI SPRPI SPRPIBI SPRUCE WILLOW
VEG_ZONEa factor with levels BOREAL_FOREST DWARF_SHRUB_TUNDRA FOREST_TUNDRA SHRUB_TUNDRA TUNDRA
LITOa numeric vector
Aga numeric vector
Ala numeric vector
Al_AAa numeric vector
Asa numeric vector
Aua numeric vector
Ba numeric vector
Baa numeric vector
Ba_AAa numeric vector
Bea numeric vector
Bia numeric vector
Bra numeric vector
Ca numeric vector
Caa numeric vector
Ca_AAa numeric vector
Cda numeric vector
Cd_AAa numeric vector
Cla numeric vector
Coa numeric vector
Co_AAa numeric vector
Conda numeric vector
Cra numeric vector
Cr_AAa numeric vector
Cua numeric vector
Cu_AAa numeric vector
Fa numeric vector
Fea numeric vector
Fe_AAa numeric vector
Ha numeric vector
Hga numeric vector
Ka numeric vector
K_AAa numeric vector
Laa numeric vector
LOIa numeric vector
Mga numeric vector
Mg_AAa numeric vector
Mna numeric vector
Mn_AAa numeric vector
Moa numeric vector
Na numeric vector
Naa numeric vector
Na_AAa numeric vector
Nia numeric vector
Ni_AAa numeric vector
NO3a numeric vector
Pa numeric vector
P_AAa numeric vector
Pba numeric vector
Pb_AAa numeric vector
Pda numeric vector
pHa numeric vector
PO4a numeric vector
Pta numeric vector
Rba numeric vector
Sa numeric vector
S_AAa numeric vector
Sba numeric vector
Sca numeric vector
Sea numeric vector
Sia numeric vector
Si_AAa numeric vector
SO4a numeric vector
Sra numeric vector
Sr_AAa numeric vector
Tha numeric vector
Ti_AAa numeric vector
Tla numeric vector
Ua numeric vector
Va numeric vector
V_AAa numeric vector
Ya numeric vector
Zna numeric vector
Zn_AAa numeric vector
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
Kola Project (1993-1998)
Reimann C, ?yr?s M, Chekushin V, Bogatyrev I, Boyd R, Caritat P de, Dutter R, Finne TE, Halleraker JH, J?ger ?, Kashulina G, Lehto O, Niskavaara H, Pavlov V, R?is?nen ML, Strand T, Volden T. Environmental Geochemical Atlas of the Central Barents Region. NGU-GTK-CKE Special Publication, Geological Survey of Norway, Trondheim, Norway, 1998.
data(ohorizon) str(ohorizon)data(ohorizon) str(ohorizon)
Computes the principal factor analysis of the input data.
pfa(x, factors, data = NULL, covmat = NULL, n.obs = NA, subset, na.action, start = NULL, scores = c("none", "regression", "Bartlett"), rotation = "varimax", maxiter = 5, control = NULL, ...)pfa(x, factors, data = NULL, covmat = NULL, n.obs = NA, subset, na.action, start = NULL, scores = c("none", "regression", "Bartlett"), rotation = "varimax", maxiter = 5, control = NULL, ...)
x |
(robustly) scaled input data |
factors |
number of factors |
data |
default value is NULL |
covmat |
(robustly) computed covariance or correlation matrix |
n.obs |
number of observations |
subset |
if a subset is used |
start |
starting values |
scores |
which method should be used to calculate the scores |
rotation |
if a rotation should be made |
maxiter |
maximum number of iterations |
control |
default value is NULL |
na.action |
what to do with NA values |
... |
arguments for creating a list |
loadings |
A matrix of loadings, one column for each factor. The factors are ordered in decreasing order of sums of squares of loadings. |
uniquness |
uniquness |
correlation |
correlation matrix |
criteria |
The results of the optimization: the value of the negativ log-likelihood and information of the iterations used. |
factors |
the factors |
dof |
degrees of freedom |
method |
"principal" |
n.obs |
number of observations if available, or NA |
call |
The matched call. |
STATISTIC, PVAL
|
The significance-test statistic and p-value, if can be computed |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(moss) var=c("Ni","Cu","Mg","Rb","Mn") x=log10(moss[,var]) x.mcd=robustbase::covMcd(x,cor=TRUE) x.rsc=scale(x,x.mcd$cent,sqrt(diag(x.mcd$cov))) pfa(x.rsc,factors=2,covmat=x.mcd,scores="regression",rotation="varimax", maxit=0,start=rep(0,ncol(x.rsc)))data(moss) var=c("Ni","Cu","Mg","Rb","Mn") x=log10(moss[,var]) x.mcd=robustbase::covMcd(x,cor=TRUE) x.rsc=scale(x,x.mcd$cent,sqrt(diag(x.mcd$cov))) pfa(x.rsc,factors=2,covmat=x.mcd,scores="regression",rotation="varimax", maxit=0,start=rep(0,ncol(x.rsc)))
Plots the Kola background
plotbg(map = "kola.background", which.map = c(1, 2, 3, 4), map.col = c(5, 1, 3, 4), map.lwd = c(2, 1, 2, 1), add.plot = FALSE, ...)plotbg(map = "kola.background", which.map = c(1, 2, 3, 4), map.col = c(5, 1, 3, 4), map.lwd = c(2, 1, 2, 1), add.plot = FALSE, ...)
map |
List of coordinates. For the correct format see also help(kola.background) |
which.map |
which==1 ... plot project boundary; which==2 ... plot coast line; which==3 ... plot country borders; which==4 ... plot lakes and rivers |
map.col |
Map colors to be used |
map.lwd |
Defines linestyle of the background |
add.plot |
logical. if true background is added to an existing plot |
... |
additional plot parameters, see help(par) |
Plots the background map of Kola
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
Reimann C, ?yr?s M, Chekushin V, Bogatyrev I, Boyd R, Caritat P de, Dutter R, Finne TE, Halleraker JH, J?ger ?, Kashulina G, Lehto O, Niskavaara H, Pavlov V, R?is?nen ML, Strand T, Volden T. Environmental Geochemical Atlas of the Central Barents Region. NGU-GTK-CKE Special Publication, Geological Survey of Norway, Trondheim, Norway, 1998.
data(kola.background) plotbg()data(kola.background) plotbg()
Plot the elements for the discriminant analysis. The plot is ordered in the different groups.
plotelement(da.object)plotelement(da.object)
da.object |
a object of the lda class |
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(iris3) Iris <- data.frame(rbind(iris3[,,1], iris3[,,2], iris3[,,3]), Sp = rep(c("s","c","v"), rep(50,3))) train <- sample(1:150, 75) z <- MASS::lda(Sp ~ ., Iris, prior = c(1,1,1)/3, subset = train) plotelement(z)data(iris3) Iris <- data.frame(rbind(iris3[,,1], iris3[,,2], iris3[,,3]), Sp = rep(c("s","c","v"), rep(50,3))) train <- sample(1:150, 75) z <- MASS::lda(Sp ~ ., Iris, prior = c(1,1,1)/3, subset = train) plotelement(z)
Plots an ellipse with percentage tolerance and a certain location and covariance.
plotellipse(x.loc, x.cov, perc = 0.98, col = NULL, lty = NULL)plotellipse(x.loc, x.cov, perc = 0.98, col = NULL, lty = NULL)
x.loc |
the location vector |
x.cov |
the covariance |
perc |
defines the percentage and should be a (vector of) number(s) between 0 and 1 |
col, lty
|
graphical parameters |
First the radius of the covariance is calculated and then the ellipses for the provided percentages are plotted at the certain location.
Plot with ellipse.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(moss) Ba=log10(moss[,"Ba"]) Ca=log10(moss[,"Ca"]) plot.new() plot.window(xlim=range(Ba),ylim=c(min(Ca)-1,max(Ca))) x=cbind(Ba,Ca) plotellipse(apply(x,2,mean),cov(x),perc=c(0.5,0.75,0.9,0.98))data(moss) Ba=log10(moss[,"Ba"]) Ca=log10(moss[,"Ca"]) plot.new() plot.window(xlim=range(Ba),ylim=c(min(Ca)-1,max(Ca))) x=cbind(Ba,Ca) plotellipse(apply(x,2,mean),cov(x),perc=c(0.5,0.75,0.9,0.98))
This function plots multivariate outliers. One possibility is to distinguish between outlier and no outlier. The alternative is to distinguish between the different percentils (e.g. <25%, 25%<x<50%,...).
plotmvoutlier(coord, data, quan = 1/2, alpha = 0.025, symb = FALSE, bw = FALSE, plotmap = TRUE, map = "kola.background", which.map = c(1, 2, 3, 4), map.col = c(5, 1, 3, 4), map.lwd = c(2, 1, 2, 1), pch2 = c(3, 21), cex2 = c(0.7, 0.2), col2 = c(1, 1), lcex.fac = 1, ...)plotmvoutlier(coord, data, quan = 1/2, alpha = 0.025, symb = FALSE, bw = FALSE, plotmap = TRUE, map = "kola.background", which.map = c(1, 2, 3, 4), map.col = c(5, 1, 3, 4), map.lwd = c(2, 1, 2, 1), pch2 = c(3, 21), cex2 = c(0.7, 0.2), col2 = c(1, 1), lcex.fac = 1, ...)
coord |
the coordinates for the points |
data |
the value for the different coordinates |
quan |
Number of subsets used for the robust estimation of the covariance matrix. Allowed are values between 0.5 and 1., see covMcd |
alpha |
Maximum thresholding proportion |
symb |
if FALSE, only two different symbols (outlier and no outlier) will be used |
bw |
if TRUE, symbols are in gray-scale (only if symb=TRUE) |
plotmap |
if TRUE, the map is plotted |
map |
the name of the background map |
which.map, map.col, map.lwd
|
parameters for the background plot, see plotbg |
pch2, cex2, col2
|
graphical parameters for the points |
lcex.fac |
factor for multiplication of symbol size (only if symb=TRUE) |
... |
further parameters for the plot |
The function computes a robust estimation of the covariance and then the Mahalanobis distances are calculated. With this distances the data set is divided into outliers and non outliers. If symb=FALSE only two different symbols are used otherwise different grey scales are used to distinguish the different types of outliers.
o |
returns the outliers |
md |
the square root of the Mahalanobis distance |
euclidean |
the Euclidean distance of the scaled data |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(moss) X=moss[,"XCOO"] Y=moss[,"YCOO"] el=c("Ag","As","Bi","Cd","Co","Cu","Ni") x=log10(moss[,el]) data(kola.background) plotmvoutlier(cbind(X,Y),x,symb=FALSE,map.col=c("grey","grey","grey","grey"), map.lwd=c(1,1,1,1), xlab="",ylab="",frame.plot=FALSE,xaxt="n",yaxt="n")data(moss) X=moss[,"XCOO"] Y=moss[,"YCOO"] el=c("Ag","As","Bi","Cd","Co","Cu","Ni") x=log10(moss[,el]) data(kola.background) plotmvoutlier(cbind(X,Y),x,symb=FALSE,map.col=c("grey","grey","grey","grey"), map.lwd=c(1,1,1,1), xlab="",ylab="",frame.plot=FALSE,xaxt="n",yaxt="n")
A multivariate outlier plot for each dimension is produced.
plotuniout(x, symb = FALSE, quan = 1/2, alpha = 0.025, bw = FALSE, pch2 = c(3, 1), cex2 = c(0.7, 0.4), col2 = c(1, 1), lcex.fac = 1, ...)plotuniout(x, symb = FALSE, quan = 1/2, alpha = 0.025, bw = FALSE, pch2 = c(3, 1), cex2 = c(0.7, 0.4), col2 = c(1, 1), lcex.fac = 1, ...)
x |
dataset |
symb |
if FALSE, only two different symbols (outlier and no outlier) will be used |
quan |
Number of subsets used for the robust estimation of the covariance matrix. Allowed are values between 0.5 and 1., see covMcd |
alpha |
Maximum thresholding proportion, see arw |
bw |
if TRUE, symbols are in gray-scale (only if symb=TRUE) |
pch2, cex2, col2
|
graphical parameters for the points |
lcex.fac |
factor for multiplication of symbol size (only if symb=TRUE) |
... |
further graphical parameters for the plot |
o |
returns the outliers |
md |
the square root of the Mahalanobis distance |
euclidean |
the Euclidean distance of the scaled data |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(moss) el=c("Ag","As","Bi","Cd","Co","Cu","Ni") dat=log10(moss[,el]) ans<-plotuniout(dat,symb=FALSE,cex2=c(0.9,0.1),pch2=c(3,21))data(moss) el=c("Ag","As","Bi","Cd","Co","Cu","Ni") dat=log10(moss[,el]) ans<-plotuniout(dat,symb=FALSE,cex2=c(0.9,0.1),pch2=c(3,21))
This function builds a rectangular grid and extracts points which are inside of an internal polygonal region.
polygrid(xgrid, ygrid, borders, vec.inout = FALSE, ...)polygrid(xgrid, ygrid, borders, vec.inout = FALSE, ...)
xgrid |
grid values in the x-direction. |
ygrid |
grid values in the y-direction. |
borders |
a matrix with polygon coordinates defining the borders of the region. |
vec.inout |
logical. If |
... |
currently not used (kept for back compatibility). |
The function works as follows:
First it creates a grid using the R function
expand.grid and then it uses the geoR'
internal function
.geoR_inout() which wraps usage of SpatialPoints
and over
from the package sp to extract the points
of the grid which are inside the polygon.
A list with components:
xypoly |
an |
vec.inout |
logical, a vector indicating whether each point of
the rectangular grid is inside the polygon. Only returned if |
Paulo Justiniano Ribeiro Jr. [email protected],
Peter J. Diggle [email protected].
See the package geoR.
expand.grid, over,
SpatialPoints.
poly <- matrix(c(.2, .8, .7, .1, .2, .1, .2, .7, .7, .1), ncol=2) plot(0:1, 0:1, type="n") lines(poly) poly.in <- polygrid(seq(0,1,l=11), seq(0,1,l=11), poly, vec=TRUE) points(poly.in$xy)poly <- matrix(c(.2, .8, .7, .1, .2, .1, .2, .7, .7, .1), ncol=2) plot(0:1, 0:1, type="n") lines(poly) poly.in <- polygrid(seq(0,1,l=11), seq(0,1,l=11), poly, vec=TRUE) points(poly.in$xy)
Connect the values for the elements with a polygon. Every "point" has his own shape and this demonstrates the characteristic of the point.
polys(x, scale = TRUE, labels = dimnames(x)[[1]], locations = NULL, nrow = NULL, ncol = NULL, key.loc = NULL, key.labels = dimnames(x)[[2]], key.xpd = TRUE, xlim = NULL, ylim = NULL, flip.labels = NULL, factx = 1, facty = 1, col.stars = NA, axes = FALSE, frame.plot = axes, main = NULL, sub = NULL, xlab = "", ylab = "", cex = 0.8, lwd = 1.1, lty = par("lty"), xpd = FALSE, mar = pmin(par("mar"), 1.1 + c(2 * axes + (xlab != ""), 2 * axes + (ylab != ""), 1, 0)), add = FALSE, plot = TRUE, ...)polys(x, scale = TRUE, labels = dimnames(x)[[1]], locations = NULL, nrow = NULL, ncol = NULL, key.loc = NULL, key.labels = dimnames(x)[[2]], key.xpd = TRUE, xlim = NULL, ylim = NULL, flip.labels = NULL, factx = 1, facty = 1, col.stars = NA, axes = FALSE, frame.plot = axes, main = NULL, sub = NULL, xlab = "", ylab = "", cex = 0.8, lwd = 1.1, lty = par("lty"), xpd = FALSE, mar = pmin(par("mar"), 1.1 + c(2 * axes + (xlab != ""), 2 * axes + (ylab != ""), 1, 0)), add = FALSE, plot = TRUE, ...)
x |
a matrix or a data frame |
scale |
if TRUE, the data will be scaled |
labels |
the labels for the polygons inside the map |
locations |
the locations for the polygons inside the map |
nrow, ncol
|
integers giving the number of rows and columns to use when locations=NULL. By default, 'nrow==ncol', a square layout will be used. |
key.loc |
the location for the legend |
key.labels |
the labels in the legend |
key.xpd |
A logical value or NA. If FALSE, all plotting is clipped to the plot region, if TRUE, all plotting is clipped to the figure region, and if NA, all plotting is clipped to the device region. |
flip.labels |
logical indicating if the label locations should flip up and down from diagram to diagram. |
factx |
additive factor for the x-coordinate |
facty |
magnification for the influence of the x-coordinate on the y-coordinate |
main, sub, xlab, ylab, xlim, ylim, col.stars, cex, lwd, lty, xpd, mar
|
graphical parameters and labels for the plot |
axes |
if FALSE, no axes will be drawn |
frame.plot |
if TRUE, a box will be made around the plot |
add |
if TRUE, it will be added to the plot |
plot |
nothing is plotted |
... |
further graphical parameters |
Each polygon represents one row of the input x. For the variables the values are computed and then those values are connected with a polygon. The location of the polygons can be defined by the user.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(ohorizon) X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] el=log10(ohorizon[,c("Cu","Ni","Na","Sr")]) sel <- c(3,8,22, 29, 32, 35, 43, 69, 73 ,93,109,129,130,134,168,181,183,205,211, 218,237,242,276,292,297,298,345,346,352,372,373,386,408,419,427,441,446,490, 516,535,551,556,558,564,577,584,601,612,617) x=el[sel,] plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n", xlim=c(360000,max(X))) polys(x,ncol=8,key.loc=c(15,1),factx=0.30,facty=2.0,cex=0.75,lwd=1.1)data(ohorizon) X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] el=log10(ohorizon[,c("Cu","Ni","Na","Sr")]) sel <- c(3,8,22, 29, 32, 35, 43, 69, 73 ,93,109,129,130,134,168,181,183,205,211, 218,237,242,276,292,297,298,345,346,352,372,373,386,408,419,427,441,446,490, 516,535,551,556,558,564,577,584,601,612,617) x=el[sel,] plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n", xlim=c(360000,max(X))) polys(x,ncol=8,key.loc=c(15,1),factx=0.30,facty=2.0,cex=0.75,lwd=1.1)
This function computes a PP (Probability-Probability) plot for the given dataset.
ppplot.das(x, pdist = pnorm, xlab = NULL, ylab = "Probability", line = TRUE, lwd = 2, pch = 3, cex = 0.7, cex.lab = 1, ...)ppplot.das(x, pdist = pnorm, xlab = NULL, ylab = "Probability", line = TRUE, lwd = 2, pch = 3, cex = 0.7, cex.lab = 1, ...)
x |
dataset |
pdist |
the distribution function |
xlab, ylab, lwd, pch, cex, cex.lab
|
graphical parameters |
line |
if a regression line should be added |
... |
further parameters for the probability function |
The empirical probability is calculated and compared with the comparison distribution.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(AuNEW) ppplot.das(AuNEW,pdist=plnorm,xlab="Probability of Au", ylab="Probabilities of lognormal distribution", pch=3,cex=0.7)data(AuNEW) ppplot.das(AuNEW,pdist=plnorm,xlab="Probability of Au", ylab="Probabilities of lognormal distribution", pch=3,cex=0.7)
This function produces a QP (Quantile-Probability) plot of the data.
qpplot.das(x, qdist = qnorm, probs = NULL, logx = FALSE, cex.lab = 1, xlab = NULL, ylab = "Probability [%]", line = TRUE, lwd = 2, pch = 3, logfinetick = c(10), logfinelab = c(10), cex = 0.7, xlim = NULL, ylim = NULL, gridy = TRUE, add.plot = FALSE, col = 1, ...)qpplot.das(x, qdist = qnorm, probs = NULL, logx = FALSE, cex.lab = 1, xlab = NULL, ylab = "Probability [%]", line = TRUE, lwd = 2, pch = 3, logfinetick = c(10), logfinelab = c(10), cex = 0.7, xlim = NULL, ylim = NULL, gridy = TRUE, add.plot = FALSE, col = 1, ...)
x |
data |
qdist |
The probability function with which the data should be compared. |
probs |
The selected probabilities, see details |
logx |
if TRUE, then log scale on x-axis is used |
cex.lab |
The size of the label |
xlab |
title for x-axis |
ylab |
title for y-axis |
line |
if TRUE the line will be drawn |
lwd |
the width of the line |
pch, cex, col
|
graphical parameter |
logfinetick |
how fine are the tick marks on log-scale on x-axis |
logfinelab |
how fine are the labels on log-scale on x-axis |
xlim |
the range for the x-axis |
ylim |
the range for the y-axis |
gridy |
if grid along y-axis should be drawn |
add.plot |
if TRUE the new plot is added to an old one |
... |
futher arguments for the probability function |
First the probability of the sorted input x is computed and than the selected quantiles are calculated and after that plot is produced. If probs=NULL then the 1%, 5%, 10%, 20%,...., 90%, 95% and 99% quantile is taken.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(AuNEW) qpplot.das(AuNEW,qdist=qlnorm,xlab="Au", ylab="Probabilities of lognormal distribution", pch=3,cex=0.7)data(AuNEW) qpplot.das(AuNEW,qdist=qlnorm,xlab="Au", ylab="Probabilities of lognormal distribution", pch=3,cex=0.7)
A QQ (Quantile-Quantile) plot is produced.
qqplot.das(x, distribution = "norm", ylab = deparse(substitute(x)), xlab = paste(distribution, "quantiles"), main = "", las = par("las"), datax = FALSE, envelope = 0.95, labels = FALSE, col = palette()[2], lwd = 2, pch = 1, line = c("quartiles", "robust", "none"), cex = 1, xaxt = "s", add.plot=FALSE,xlim=NULL,ylim=NULL,...)qqplot.das(x, distribution = "norm", ylab = deparse(substitute(x)), xlab = paste(distribution, "quantiles"), main = "", las = par("las"), datax = FALSE, envelope = 0.95, labels = FALSE, col = palette()[2], lwd = 2, pch = 1, line = c("quartiles", "robust", "none"), cex = 1, xaxt = "s", add.plot=FALSE,xlim=NULL,ylim=NULL,...)
x |
numeric vector |
distribution |
name of the comparison distribution |
ylab |
label for the y axis (empirical quantiles) |
xlab |
label for the x axis (comparison quantiles) |
main |
title for the plot |
las |
if 0, ticks labels are drawn parallel to the axis |
datax |
if TRUE, x and y axis are exchanged |
envelope |
confidence level for point-wise confidence envelope, or FALSE for no envelope |
labels |
vector of point labels for interactive point identification, or FALSE for no labels |
col, lwd, pch, cex, xaxt
|
graphical parameter, see par |
line |
"quartiles" to pass a line through the quartile-pairs, or "robust" for a robust-regression line. "none" suppresses the line |
add.plot |
if TRUE the new plot is added to an old one |
xlim |
the range for the x-axis |
ylim |
the range for the y-axis |
... |
further arguments for the probability function |
The probability of the input data is computed and with this result the quantiles of the comparison distribution are calculated. If line="quartiles" a line based on quartiles is plotted and if line="robust" a robust LM model is calculated.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(AuNEW) qqplot.das(AuNEW,distribution="lnorm",col=1,envelope=FALSE,datax=TRUE,ylab="Au", xlab="Quantiles of lognormal distribution", main="",line="none",pch=3,cex=0.7)data(AuNEW) qqplot.das(AuNEW,distribution="lnorm",col=1,envelope=FALSE,datax=TRUE,ylab="Au", xlab="Quantiles of lognormal distribution", main="",line="none",pch=3,cex=0.7)
This result could also be directly computed using the function eyefit.
data(res.eyefit.As_C)data(res.eyefit.As_C)
The format is: List of 1 $ :List of 7 ..$ cov.model: chr "spherical" ..$ cov.pars : num [1:2] 0.8 160.3 ..$ nugget : num 0.49 ..$ kappa : num 0.5 ..$ lambda : num 0 ..$ trend : chr "cte" ..$ max.dist : num 288 ..- attr(*, "class")= chr "variomodel" - attr(*, "class")= chr "eyefit"
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(res.eyefit.As_C) str(res.eyefit.As_C)data(res.eyefit.As_C) str(res.eyefit.As_C)
This result could also be directly computed using the function eyefit.
data(res.eyefit.As_C_m)data(res.eyefit.As_C_m)
The format is: List of 1 $ :List of 7 ..$ cov.model: chr "spherical" ..$ cov.pars : num [1:2] 0.8 160255.8 ..$ nugget : num 0.49 ..$ kappa : num 0.5 ..$ lambda : num 0 ..$ trend : chr "cte" ..$ max.dist : num 288460 ..- attr(*, "class")= chr "variomodel" - attr(*, "class")= chr "eyefit"
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(res.eyefit.As_C_m) str(res.eyefit.As_C_m)data(res.eyefit.As_C_m) str(res.eyefit.As_C_m)
This result could also be directly computed using the function eyefit.
data(res.eyefit.AuNEW)data(res.eyefit.AuNEW)
The format is: List of 1 $ :List of 7 ..$ cov.model: chr "exponential" ..$ cov.pars : num [1:2] 0.31 53418.46 ..$ nugget : num 0.44 ..$ kappa : num 0.5 ..$ lambda : num 0 ..$ trend : chr "cte" ..$ max.dist : num 192306 ..- attr(*, "class")= chr "variomodel" - attr(*, "class")= chr "eyefit"
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(res.eyefit.AuNEW) str(res.eyefit.AuNEW)data(res.eyefit.AuNEW) str(res.eyefit.AuNEW)
This result could also be directly computed using the function eyefit.
data(res.eyefit.Ca_C)data(res.eyefit.Ca_C)
The format is: List of 1 $ :List of 7 ..$ cov.model: chr "spherical" ..$ cov.pars : num [1:2] 3.80e-01 1.92e+05 ..$ nugget : num 0.21 ..$ kappa : num 0.5 ..$ lambda : num 0 ..$ trend : chr "cte" ..$ max.dist : num 192306 ..- attr(*, "class")= chr "variomodel" - attr(*, "class")= chr "eyefit"
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(res.eyefit.Ca_C) str(res.eyefit.Ca_C)data(res.eyefit.Ca_C) str(res.eyefit.Ca_C)
This result could also be directly computed using the function eyefit.
data(res.eyefit.Ca_O)data(res.eyefit.Ca_O)
The format is: List of 1 $ :List of 7 ..$ cov.model: chr "spherical" ..$ cov.pars : num [1:2] 0.01 5341.85 ..$ nugget : num 0.12 ..$ kappa : num 0.5 ..$ lambda : num 0 ..$ trend : chr "cte" ..$ max.dist : num 192306 ..- attr(*, "class")= chr "variomodel" - attr(*, "class")= chr "eyefit"
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(res.eyefit.Ca_O) str(res.eyefit.Ca_O)data(res.eyefit.Ca_O) str(res.eyefit.Ca_O)
This result could also be directly computed using the function eyefit.
data(res.eyefit.Hg_O)data(res.eyefit.Hg_O)
The format is: List of 1 $ :List of 7 ..$ cov.model: chr "exponential" ..$ cov.pars : num [1:2] 1.50e-02 3.21e+04 ..$ nugget : num 0.04 ..$ kappa : num 0.5 ..$ lambda : num 0 ..$ trend : chr "cte" ..$ max.dist : num 288460 ..- attr(*, "class")= chr "variomodel" - attr(*, "class")= chr "eyefit"
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(res.eyefit.Hg_O) str(res.eyefit.Hg_O)data(res.eyefit.Hg_O) str(res.eyefit.Hg_O)
This result could also be directly computed using the function eyefit.
data(res.eyefit.Pb_O1)data(res.eyefit.Pb_O1)
The format is: List of 1 $ :List of 7 ..$ cov.model: chr "spherical" ..$ cov.pars : num [1:2] 1.90e-01 5.13e+05 ..$ nugget : num 0.11 ..$ kappa : num 0.5 ..$ lambda : num 0 ..$ trend : chr "cte" ..$ max.dist : num 288460 ..- attr(*, "class")= chr "variomodel" - attr(*, "class")= chr "eyefit"
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(res.eyefit.Pb_O1) str(res.eyefit.Pb_O1)data(res.eyefit.Pb_O1) str(res.eyefit.Pb_O1)
This result could also be directly computed using the function eyefit.
data(res.eyefit.Pb_O2)data(res.eyefit.Pb_O2)
The format is: List of 1 $ :List of 7 ..$ cov.model: chr "spherical" ..$ cov.pars : num [1:2] 0.03 48076.64 ..$ nugget : num 0.11 ..$ kappa : num 0.5 ..$ lambda : num 0 ..$ trend : chr "cte" ..$ max.dist : num 288460 ..- attr(*, "class")= chr "variomodel" - attr(*, "class")= chr "eyefit"
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(res.eyefit.Pb_O2) str(res.eyefit.Pb_O2)data(res.eyefit.Pb_O2) str(res.eyefit.Pb_O2)
Plot a single horizontal boxplot, the default is a Tukey boxplot.
rg.boxplot(xx, xlab = deparse(substitute(xx)), log = FALSE, ifbw = FALSE, wend = 0.05, xlim = NULL, main = " ", colr = 5, ...)rg.boxplot(xx, xlab = deparse(substitute(xx)), log = FALSE, ifbw = FALSE, wend = 0.05, xlim = NULL, main = " ", colr = 5, ...)
xx |
data |
xlab |
label for the x-axis |
log |
if TRUE, a log-scaled plot and a logtransformation of the data |
ifbw |
if TRUE, a IDEAS style box-and-whisker plot is produced |
wend |
defines the end of the whisker, default is 5% and 95% quantile |
xlim |
setting xlim results in outliers not being plotted as the x-axis is shortened. |
main |
main title of the plot |
colr |
the box is infilled with a yellow ochre; if no colour is required set colr=0 |
... |
further graphical parameters for the plot |
As the x-axis is shortend by setting xlim, however, the statistics used to define the boxplot, or box-and-whisker plot, are still based on the total data set. To plot a truncated data set create a subset first, or use the x[x<some.value] construct in the call.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(chorizon) Ba=chorizon[,"Ba"] rg.boxplot(Ba,ifbw=TRUE,colr=0,xlab="Ba [mg/kg]",cex.lab=1.2)data(chorizon) Ba=chorizon[,"Ba"] rg.boxplot(Ba,ifbw=TRUE,colr=0,xlab="Ba [mg/kg]",cex.lab=1.2)
Procedure to undertake non-robust multivariate data analysis. The saved list may be passed to other rotation and display functions
rg.mva(x, main = deparse(substitute(x)))rg.mva(x, main = deparse(substitute(x)))
x |
data |
main |
used for the list |
Procesure to undertake non-robust multivariate data analyses; the object generated is identical to that of rg.robmva so that the savedlist may be passed to other rotation and display functions. Thus weights are set to 1, and other variables are set to appropriate defaults. The estimation of Mahalanobis distances is only undertaken if x is nonsingular, i.e. the lowest eigenvalue is > 10e-4.
n |
number of rows |
p |
number of columns |
wts |
the weights for the covariance matrix |
mean |
the mean of the data |
cov |
the covariance |
sd |
the standard deviation |
r |
correlation matrix |
eigenvalues |
eigenvalues of the SVD |
econtrib |
proportion of eigenvalues in % |
eigenvectors |
eigenvectors of the SVD |
rload |
loadings matrix |
rcr |
standardised loadings matrix |
vcontrib |
scores variance |
pvcontrib |
proportion of scores variance in % |
cpvcontrib |
cummulative proportion of scores variance |
md |
Mahalanbois distance |
ppm |
probability for outliegness using F-distribution |
epm |
probability for outliegness using Chisquared-distribution |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
#input data data(ohorizon) vegzn=ohorizon[,"VEG_ZONE"] veg=rep(NA,nrow(ohorizon)) veg[vegzn=="BOREAL_FOREST"] <- 1 veg[vegzn=="FOREST_TUNDRA"] <- 2 veg[vegzn=="SHRUB_TUNDRA"] <- 3 veg[vegzn=="DWARF_SHRUB_TUNDRA"] <- 3 veg[vegzn=="TUNDRA"] <- 3 el=c("Ag","Al","As","B","Ba","Bi","Ca","Cd","Co","Cu","Fe","K","Mg","Mn", "Na","Ni","P","Pb","Rb","S","Sb","Sr","Th","Tl","V","Y","Zn") x <- log10(ohorizon[!is.na(veg),el]) v <- veg[!is.na(veg)] rg.mva(as.matrix(x[v==1,]))#input data data(ohorizon) vegzn=ohorizon[,"VEG_ZONE"] veg=rep(NA,nrow(ohorizon)) veg[vegzn=="BOREAL_FOREST"] <- 1 veg[vegzn=="FOREST_TUNDRA"] <- 2 veg[vegzn=="SHRUB_TUNDRA"] <- 3 veg[vegzn=="DWARF_SHRUB_TUNDRA"] <- 3 veg[vegzn=="TUNDRA"] <- 3 el=c("Ag","Al","As","B","Ba","Bi","Ca","Cd","Co","Cu","Fe","K","Mg","Mn", "Na","Ni","P","Pb","Rb","S","Sb","Sr","Th","Tl","V","Y","Zn") x <- log10(ohorizon[!is.na(veg),el]) v <- veg[!is.na(veg)] rg.mva(as.matrix(x[v==1,]))
Function to allocate an individual to one of several populations.
rg.mvalloc(pcrit = 0.05, x, ...)rg.mvalloc(pcrit = 0.05, x, ...)
pcrit |
When the probability of group membership is less than pcrit it is allocated to group 0. |
x |
contains the individuals to be allocated |
... |
arguments for creating a list of groups |
m objects are the reference populations generated by md.gait, rg.robmva or rg.mva to estimate Mahalanobis distancesand predicted probabilities of group membership for individuals in matrix x. Note that the log |determinant| of the appropriate covariance matrix is added to the Mahalanobis distance on the assumption that the covariance matrices are inhomogeneous. If the data require transformation this must be undertaken before calling this function. This implies that a similar transformation must have been used for all the reference data subsets.
groups |
the groups |
m |
number of groups |
n |
number of individuals to be allocated |
p |
number of columns |
pgm |
number of individuals to be allocated multiplied with the groups |
pcrit |
critical probability |
xalloc |
number of individuals as integer |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
#input data data(ohorizon) vegzn=ohorizon[,"VEG_ZONE"] veg=rep(NA,nrow(ohorizon)) veg[vegzn=="BOREAL_FOREST"] <- 1 veg[vegzn=="FOREST_TUNDRA"] <- 2 veg[vegzn=="SHRUB_TUNDRA"] <- 3 veg[vegzn=="DWARF_SHRUB_TUNDRA"] <- 3 veg[vegzn=="TUNDRA"] <- 3 el=c("Ag","Al","As","B","Ba","Bi","Ca","Cd","Co","Cu","Fe","K","Mg","Mn", "Na","Ni","P","Pb","Rb","S","Sb","Sr","Th","Tl","V","Y","Zn") x <- log10(ohorizon[!is.na(veg),el]) v <- veg[!is.na(veg)] res.zone1=rg.mva(as.matrix(x[v==1,])) res.zone2=rg.mva(as.matrix(x[v==2,])) res.zone3=rg.mva(as.matrix(x[v==3,])) res=rg.mvalloc(pcrit=0.01,x,res.zone1,res.zone2,res.zone3)#input data data(ohorizon) vegzn=ohorizon[,"VEG_ZONE"] veg=rep(NA,nrow(ohorizon)) veg[vegzn=="BOREAL_FOREST"] <- 1 veg[vegzn=="FOREST_TUNDRA"] <- 2 veg[vegzn=="SHRUB_TUNDRA"] <- 3 veg[vegzn=="DWARF_SHRUB_TUNDRA"] <- 3 veg[vegzn=="TUNDRA"] <- 3 el=c("Ag","Al","As","B","Ba","Bi","Ca","Cd","Co","Cu","Fe","K","Mg","Mn", "Na","Ni","P","Pb","Rb","S","Sb","Sr","Th","Tl","V","Y","Zn") x <- log10(ohorizon[!is.na(veg),el]) v <- veg[!is.na(veg)] res.zone1=rg.mva(as.matrix(x[v==1,])) res.zone2=rg.mva(as.matrix(x[v==2,])) res.zone3=rg.mva(as.matrix(x[v==3,])) res=rg.mvalloc(pcrit=0.01,x,res.zone1,res.zone2,res.zone3)
Function to remove NAs from a vector and inform the user of how many.
rg.remove.na(xx)rg.remove.na(xx)
xx |
vector |
The function counts the NAs in a vector and returns the number of NAs and the "new" vector.
x |
vector without the NAs |
nna |
number of NAs removed |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
x<-rep(NA,10) x[c(1,3,5,7,9)]<-10 rg.remove.na(x)x<-rep(NA,10) x[c(1,3,5,7,9)]<-10 rg.remove.na(x)
Procedure for multivariate analysis using the minimum volume ellipsoid (MVE), minimum covariance determinant (MCD) or a supplied set of 0-1 weights.
rg.robmva(x, proc = "mcd", wts = NULL, main = deparse(substitute(x)))rg.robmva(x, proc = "mcd", wts = NULL, main = deparse(substitute(x)))
x |
data |
proc |
procedure for the estimation (MVE or MCD) |
wts |
if proc=NULL, the supplied weights for the calculation |
main |
input for the list |
cov.mcd is limited to a maximum of 50 variables. Both of these procedures lead to a vector of 0-1 weights and mcd is the default. A set of weights can be generated by using Graphical Adaptive Interactive Trimming (GAIT) procedure available though rg.md.gait(). Using 0-1 weights the parameters of the background distribution are estimated by cov.wt(). A robust estimation of the Mahalanobis distances is made for the total data set but is only undertaken if x is non-singular (lowest eigenvalue is >10e-4).
n |
number of rows |
p |
number of columns |
wts |
the weights for the covariance matrix |
mean |
the mean of the data |
cov |
the covariance |
sd |
the standard deviation |
r |
correlation matrix |
eigenvalues |
eigenvalues of the SVD |
econtrib |
proportion of eigenvalues in % |
eigenvectors |
eigenvectors of the SVD |
rload |
loadings matrix |
rcr |
standardised loadings matrix |
vcontrib |
scores variance |
pvcontrib |
proportion of scores variance in % |
cpvcontrib |
cummulative proportion of scores variance |
md |
Mahalanbois distance |
ppm |
probability for outliegness using F-distribution |
epm |
probability for outliegness using Chisquared-distribution |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
#input data data(ohorizon) vegzn=ohorizon[,"VEG_ZONE"] veg=rep(NA,nrow(ohorizon)) veg[vegzn=="BOREAL_FOREST"] <- 1 veg[vegzn=="FOREST_TUNDRA"] <- 2 veg[vegzn=="SHRUB_TUNDRA"] <- 3 veg[vegzn=="DWARF_SHRUB_TUNDRA"] <- 3 veg[vegzn=="TUNDRA"] <- 3 el=c("Ag","Al","As","B","Ba","Bi","Ca","Cd","Co","Cu","Fe","K","Mg","Mn", "Na","Ni","P","Pb","Rb","S","Sb","Sr","Th","Tl","V","Y","Zn") x <- log10(ohorizon[!is.na(veg),el]) v <- veg[!is.na(veg)] subvar=c("Ag","B","Bi","Mg","Mn","Na","Pb","Rb","S","Sb","Tl") set.seed(100) rg.robmva(as.matrix(x[v==1,subvar]))#input data data(ohorizon) vegzn=ohorizon[,"VEG_ZONE"] veg=rep(NA,nrow(ohorizon)) veg[vegzn=="BOREAL_FOREST"] <- 1 veg[vegzn=="FOREST_TUNDRA"] <- 2 veg[vegzn=="SHRUB_TUNDRA"] <- 3 veg[vegzn=="DWARF_SHRUB_TUNDRA"] <- 3 veg[vegzn=="TUNDRA"] <- 3 el=c("Ag","Al","As","B","Ba","Bi","Ca","Cd","Co","Cu","Fe","K","Mg","Mn", "Na","Ni","P","Pb","Rb","S","Sb","Sr","Th","Tl","V","Y","Zn") x <- log10(ohorizon[!is.na(veg),el]) v <- veg[!is.na(veg)] subvar=c("Ag","B","Bi","Mg","Mn","Na","Pb","Rb","S","Sb","Tl") set.seed(100) rg.robmva(as.matrix(x[v==1,subvar]))
This function computes a weighted sum for a matrix based on computed quantiles and user defined relative importance.
rg.wtdsums(x, ri, xcentr = NULL, xdisp = NULL)rg.wtdsums(x, ri, xcentr = NULL, xdisp = NULL)
x |
matrix |
ri |
vector for the relative importance, length(ri)=length(x[1,]) |
xcentr |
the provided center |
xdisp |
the provided variance |
It is not necessary to provide the center and the variance. If those values are not supplied the center is the 50% quantile and the variance is calculated from the 25% and 75% quantile.
input |
input parameter |
centr |
the center |
disp |
the variance |
ri |
relative importance |
w |
weights |
a |
normalized weights |
ws |
normalized weights times standardized x |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(chorizon) var=c("Si_XRF","Al_XRF","K_XRF","LOI","P","Mn") ri=c(-2.0,1.5,2.0,2.0,3.0,2.0) x=chorizon[,var] rg.wtdsums(x,ri)data(chorizon) var=c("Si_XRF","Al_XRF","K_XRF","LOI","P","Mn") ri=c(-2.0,1.5,2.0,2.0,3.0,2.0) x=chorizon[,var] rg.wtdsums(x,ri)
This function compares a robust covariance (correlation) estimation (MCD is used) with the classical approach. A plot with the two ellipses will be produced and the correlation coefficients are quoted.
RobCor.plot(x, y, quan = 1/2, alpha = 0.025, colC = 1, colR = 1, ltyC = 2, ltyR = 1, ...)RobCor.plot(x, y, quan = 1/2, alpha = 0.025, colC = 1, colR = 1, ltyC = 2, ltyR = 1, ...)
x, y
|
two data vectors where the correlation should be computed |
quan |
fraction of tolerated outliers (at most 0.5) |
alpha |
quantile of chisquare distribution for outlier cutoff |
colC, colR
|
colour for both ellipses |
ltyC, ltyR
|
line type for both ellipses |
... |
other graphical parameters |
The covariance matrix is estimated in a robust (MCD) and non robust way and then both ellipses are plotted. The radi is calculated from the singular value decomposition and a breakpoint (specified quantile) for outlier cutoff.
cor.cla |
correlation of the classical estimation |
cor.rob |
correlation of the robust estimation |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(chorizon) Be=chorizon[,"Be"] Sr=chorizon[,"Sr"] RobCor.plot(log10(Be),log10(Sr),xlab="Be in C-horizon [mg/kg]", ylab="Sr in C-horizon [mg/kg]",cex.lab=1.2, pch=3, cex=0.7, xaxt="n", yaxt="n",colC=1,colR=1,ltyC=2,ltyR=1)data(chorizon) Be=chorizon[,"Be"] Sr=chorizon[,"Sr"] RobCor.plot(log10(Be),log10(Sr),xlab="Be in C-horizon [mg/kg]", ylab="Sr in C-horizon [mg/kg]",cex.lab=1.2, pch=3, cex=0.7, xaxt="n", yaxt="n",colC=1,colR=1,ltyC=2,ltyR=1)
Round a value in a pretty way.
roundpretty(kvec, maxdig)roundpretty(kvec, maxdig)
kvec |
the variable to be rounded |
maxdig |
maximum number of digits after the coma |
result |
rounded value |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
roundpretty(0.873463029,5) roundpretty(0.073463029,5) roundpretty(0.003463029,5) roundpretty(0.000463029,5)roundpretty(0.873463029,5) roundpretty(0.073463029,5) roundpretty(0.003463029,5) roundpretty(0.000463029,5)
This function rounds the number in pretty way.
roundpretty.sub(k, maxdig)roundpretty.sub(k, maxdig)
k |
number to be rounded pretty |
maxdig |
maximum number of digits after the coma |
When maxdig is larger than 8 and the number is smaller than 0.00001, the number is rounded to 8 numbers after the coma. When the number ist smaller than 0.0001 the maximum numbers after the coma is 7, and so on.
kr |
rounded value |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
This function plots the unit at a specified location.
scalebar(Xlowerleft, Ylowerleft, Xupperright, Yupperright, shifttext, shiftkm, sizetext)scalebar(Xlowerleft, Ylowerleft, Xupperright, Yupperright, shifttext, shiftkm, sizetext)
Xlowerleft, Ylowerleft
|
x and y coordinate of the lower left corner |
Xupperright, Yupperright
|
x and y coordinate of the upper corner |
shifttext |
on which margin line, starting at 0 counting outwards |
shiftkm |
how far from the last point the label should be written |
sizetext |
expansion factor for the text |
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
plot.new() scalebar(0,0.25,1,0.5,shifttext=-0.05,shiftkm=4e4,sizetext=0.8)plot.new() scalebar(0,0.25,1,0.5,shifttext=-0.05,shiftkm=4e4,sizetext=0.8)
This function makes a 3D plot of the data and the regression function. The user has the choice between different methods to calculate the coefficients for the regression model.
scatter3dPETER(x, y, z, xlab = deparse(substitute(x)), ylab = deparse(substitute(y)), zlab = deparse(substitute(z)), revolutions = 0, bg.col = c("white", "black"), axis.col = if (bg.col == "white") "black" else "white", surface.col = c("blue", "green", "orange", "magenta", "cyan", "red", "yellow", "gray"), neg.res.col = "red", pos.res.col = "green", point.col = "yellow", text.col = axis.col, grid.col = if (bg.col == "white") "black" else "gray", fogtype = c("exp2", "linear", "exp", "none"), residuals = (length(fit) == 1), surface = TRUE, grid = TRUE, grid.lines = 26, df.smooth = NULL, df.additive = NULL, sphere.size = 1, threshold = 0.01, speed = 1, fov = 60, fit = "linear", groups = NULL, parallel = TRUE, model.summary = FALSE)scatter3dPETER(x, y, z, xlab = deparse(substitute(x)), ylab = deparse(substitute(y)), zlab = deparse(substitute(z)), revolutions = 0, bg.col = c("white", "black"), axis.col = if (bg.col == "white") "black" else "white", surface.col = c("blue", "green", "orange", "magenta", "cyan", "red", "yellow", "gray"), neg.res.col = "red", pos.res.col = "green", point.col = "yellow", text.col = axis.col, grid.col = if (bg.col == "white") "black" else "gray", fogtype = c("exp2", "linear", "exp", "none"), residuals = (length(fit) == 1), surface = TRUE, grid = TRUE, grid.lines = 26, df.smooth = NULL, df.additive = NULL, sphere.size = 1, threshold = 0.01, speed = 1, fov = 60, fit = "linear", groups = NULL, parallel = TRUE, model.summary = FALSE)
x, y, z
|
the coordinates for the points |
xlab, ylab, zlab
|
the labels for the axis |
revolutions |
if the plot should be viewed from different angles |
bg.col, axis.col, surface.col, point.col, text.col, grid.col
|
define the colour for the background, axis,... |
pos.res.col, neg.res.col
|
colour for positive and negativ residuals |
fogtype |
describes the fogtype, see rgl.bg |
residuals |
if the residuals should be plotted |
surface |
if the regression function should be plotted or just the points |
grid |
if TRUE, the grid is plotted |
grid.lines |
number of lines in the grid |
df.smooth |
if fit=smooth, the number of degrees of freedom |
df.additive |
if fit=additive, the number of degrees of freedom |
sphere.size |
a value for calibrating the size of the sphere |
threshold |
the minimum size of the sphere, if the size is smaller than the threshold a point is plotted |
speed |
if revolutions>0, how fast you make a 360 degree turn |
fov |
field-of-view angle, see rgl.viewpoint |
fit |
which method should be used for the model; "linear", "quadratic", "smooth" or "additive" |
groups |
define groups for the points |
parallel |
if groups is not NULL, a parallel shift in the model is made |
model.summary |
if the summary should be returned |
The user can choose between a linear, quadratic, smoothed or additve model to calculate the coefficients.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
#required library #require(IPSUR) data(chorizon) lit=1 # This example needs additional libraries: #scatter3dPETER(x=log10(chorizon[chorizon$LITO==lit,"Cr"]), # z=log10(chorizon[chorizon$LITO==lit,"Cr_INAA"]), # y=log10(chorizon[chorizon$LITO==lit,"Co"]), # xlab="",ylab="",zlab="", # neg.res.col=gray(0.6), pos.res.col=gray(0.1), point.col=1, fov=30, # surface.col="black",grid.col="gray",sphere.size=0.8)#required library #require(IPSUR) data(chorizon) lit=1 # This example needs additional libraries: #scatter3dPETER(x=log10(chorizon[chorizon$LITO==lit,"Cr"]), # z=log10(chorizon[chorizon$LITO==lit,"Cr_INAA"]), # y=log10(chorizon[chorizon$LITO==lit,"Co"]), # xlab="",ylab="",zlab="", # neg.res.col=gray(0.6), pos.res.col=gray(0.1), point.col=1, fov=30, # surface.col="black",grid.col="gray",sphere.size=0.8)
Plots smoothing maps and legend based on continuous or percentile scale.
SmoothLegend(X, Y, z, resol = 200, type = "percentile", whichcol = "gray", qutiles = c(0, 0.05, 0.25, 0.5, 0.75, 0.9, 0.95, 1), borders=NULL, leg.xpos.min = 780000, leg.xpos.max = 8e+05, leg.ypos.min = 7760000, leg.ypos.max = 7870000, leg.title = "mg/kg", leg.title.cex = 0.7, leg.numb.cex = 0.7, leg.round = 2, leg.wid = 4, leg.numb.xshift = 70000, leg.perc.xshift = 40000, leg.perc.yshift = 20000, tit.xshift = 35000)SmoothLegend(X, Y, z, resol = 200, type = "percentile", whichcol = "gray", qutiles = c(0, 0.05, 0.25, 0.5, 0.75, 0.9, 0.95, 1), borders=NULL, leg.xpos.min = 780000, leg.xpos.max = 8e+05, leg.ypos.min = 7760000, leg.ypos.max = 7870000, leg.title = "mg/kg", leg.title.cex = 0.7, leg.numb.cex = 0.7, leg.round = 2, leg.wid = 4, leg.numb.xshift = 70000, leg.perc.xshift = 40000, leg.perc.yshift = 20000, tit.xshift = 35000)
X |
X-coordinates |
Y |
Y-coordinates |
z |
values on the coordinates |
resol |
resolution of smoothing |
type |
"percentile" for percentile legend; "contin" for continuous grey-scale or colour map |
whichcol |
type of color scheme to use: "grey", "rainbow", "rainbow.trunc", "rainbow.inv", "terrain" or "topo" |
qutiles |
considered quantiles if type="percentile" is used |
borders |
either NULL or character string with the name of the list with list elements x and y for x- and y-coordinates of map borders |
leg.xpos.min |
minimum value of x-position of the legend |
leg.xpos.max |
maximum value of x-position of the legend |
leg.ypos.min |
minimum value of y-position of the legend |
leg.ypos.max |
maximum value of y-position of the legend |
leg.title |
title for legend |
leg.title.cex |
cex for legend title |
leg.numb.cex |
cex for legend numbers |
leg.round |
round legend to specified digits "pretty" |
leg.wid |
width (space in numbers) for legend |
leg.numb.xshift |
x-shift of numbers in legend relative to leg.xpos.max |
leg.perc.xshift |
x-shift of "Percentile" in legend relative to leg.xpos.min |
leg.perc.yshift |
y-shift of "Percentile" in legend relative to leg.ypos.max |
tit.xshift |
x-shift of title in legend relative to leg.xpos.max |
First a interpolation is applied using different versions of algorithms from Akima and then all points a distinguished into inside an outside the polygonal region. Now the empirical quantiles for points inside the polygon are computed and then the values are plotted in different scales of the choosen colour. ATTENTION: here borders were defined for the smoothing region
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(chorizon) X=chorizon[,"XCOO"] Y=chorizon[,"YCOO"] el=log10(chorizon[,"As"]) # generate plot plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n") data(bordersKola) # list with list elements x and y for x- and y-corrdinates of map borders SmoothLegend(X,Y,el,resol=200,type="contin",whichcol="gray", qutiles=c(0,0.05,0.25,0.50,0.75,0.90,0.95,1), borders="bordersKola", leg.xpos.min=7.8e5,leg.xpos.max=8.0e5,leg.ypos.min=77.6e5,leg.ypos.max=78.7e5, leg.title="mg/kg", leg.title.cex=0.7, leg.numb.cex=0.7, leg.round=2,leg.wid=4, leg.numb.xshift=0.7e5,leg.perc.xshift=0.4e5,leg.perc.yshift=0.2e5,tit.xshift=0.35e5) # plot background data(kola.background) plotbg(map.col=c("gray","gray","gray","gray"),map.lwd=c(1,1,1,1),add.plot=TRUE)data(chorizon) X=chorizon[,"XCOO"] Y=chorizon[,"YCOO"] el=log10(chorizon[,"As"]) # generate plot plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n") data(bordersKola) # list with list elements x and y for x- and y-corrdinates of map borders SmoothLegend(X,Y,el,resol=200,type="contin",whichcol="gray", qutiles=c(0,0.05,0.25,0.50,0.75,0.90,0.95,1), borders="bordersKola", leg.xpos.min=7.8e5,leg.xpos.max=8.0e5,leg.ypos.min=77.6e5,leg.ypos.max=78.7e5, leg.title="mg/kg", leg.title.cex=0.7, leg.numb.cex=0.7, leg.round=2,leg.wid=4, leg.numb.xshift=0.7e5,leg.perc.xshift=0.4e5,leg.perc.yshift=0.2e5,tit.xshift=0.35e5) # plot background data(kola.background) plotbg(map.col=c("gray","gray","gray","gray"),map.lwd=c(1,1,1,1),add.plot=TRUE)
This function makes a graphical diagram of multivariate data. Every element represents one line in the sun and the length of the line indicates the concentration of the element.
suns(x, full = TRUE, scale = TRUE, radius = TRUE, labels = dimnames(x)[[1]], locations = NULL, nrow = NULL, ncol = NULL, len = 1, key.loc = NULL, key.labels = dimnames(x)[[2]], key.xpd = TRUE, xlim = NULL, ylim = NULL, flip.labels = NULL, col.stars = NA, axes = FALSE, frame.plot = axes, main = NULL, sub = NULL, xlab = "", ylab = "", cex = 0.8, lwd = 0.25, lty = par("lty"), xpd = FALSE, mar = pmin(par("mar"), 1.1 + c(2 * axes + (xlab != ""), 2 * axes + (ylab != ""), 1, 0)), add = FALSE, plot = TRUE, ...)suns(x, full = TRUE, scale = TRUE, radius = TRUE, labels = dimnames(x)[[1]], locations = NULL, nrow = NULL, ncol = NULL, len = 1, key.loc = NULL, key.labels = dimnames(x)[[2]], key.xpd = TRUE, xlim = NULL, ylim = NULL, flip.labels = NULL, col.stars = NA, axes = FALSE, frame.plot = axes, main = NULL, sub = NULL, xlab = "", ylab = "", cex = 0.8, lwd = 0.25, lty = par("lty"), xpd = FALSE, mar = pmin(par("mar"), 1.1 + c(2 * axes + (xlab != ""), 2 * axes + (ylab != ""), 1, 0)), add = FALSE, plot = TRUE, ...)
x |
a matrix or a data frame |
full |
if TRUE, a whole circle will be made |
scale |
if TRUE, the data will be scaled |
radius |
should be TRUE, otherwise the lines in the sun will not be plotted |
labels |
the labels for the suns inside the map |
locations |
the locations for the suns inside the map |
nrow, ncol
|
integers giving the number of rows and columns to use when locations=NULL |
len |
scaling factor for the length of the lines (according to the size of the map) |
key.loc |
the location for the legend |
key.labels |
the labels in the legend |
key.xpd |
A logical value or NA. If FALSE, all plotting is clipped to the plot region, if TRUE, all plotting is clipped to the figure region, and if NA, all plotting is clipped to the device region. |
flip.labels |
logical indication if the label locations should flip up and down from diagram to diagram. |
axes |
if FALSE, no axes will be drawn |
frame.plot |
if TRUE, a box will be made around the plot |
main, sub, xlab, xlim, ylim, col.stars, ylab, cex, lwd, lty, xpd, mar
|
graphical parameters and labels for the plot |
add |
if TRUE, it will be added to the plot |
plot |
nothing is plotted |
... |
graphical parameters for plotting the box |
Each sun represents one row of the input x. Each line of the sun represents one choosen element. The distance from the center of the sun to the point shows the size of the value of the (scaled) column.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(ohorizon) X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] el=log10(ohorizon[,c("Co","Cu","Ni","Rb","Bi","Na","Sr")]) sel <- c(3,8,22, 29, 32, 35, 43, 69, 73 ,93,109,129,130,134,168,181,183,205,211, 218,237,242,276,292,297,298,345,346,352,372,373,386,408,419,427,441,446,490, 516,535,551,556,558,564,577,584,601,612,617) x=el[sel,] suns(x,ncol=8,key.loc=c(15,0.5),lwd=1.3)data(ohorizon) X=ohorizon[,"XCOO"] Y=ohorizon[,"YCOO"] el=log10(ohorizon[,c("Co","Cu","Ni","Rb","Bi","Na","Sr")]) sel <- c(3,8,22, 29, 32, 35, 43, 69, 73 ,93,109,129,130,134,168,181,183,205,211, 218,237,242,276,292,297,298,345,346,352,372,373,386,408,419,427,441,446,490, 516,535,551,556,558,564,577,584,601,612,617) x=el[sel,] suns(x,ncol=8,key.loc=c(15,0.5),lwd=1.3)
Plots symbols and Legend on a map. There are two different methods (percentile symbols or boxplot symbols) to display the legend.
SymbLegend(X, Y, z, type = "percentile", qutiles = c(0, 0.05, 0.25, 0.75, 0.95, 1), q = NULL, symbtype = "EDA", symbmagn = 0.8, leg.position = "topright", leg.title = "", leg.title.cex = 0.8, leg.round = 2, leg.wid = 4, leg.just = "right", cex.scale = 0.8, xf = 9000, logscale = TRUE, accentuate = FALSE)SymbLegend(X, Y, z, type = "percentile", qutiles = c(0, 0.05, 0.25, 0.75, 0.95, 1), q = NULL, symbtype = "EDA", symbmagn = 0.8, leg.position = "topright", leg.title = "", leg.title.cex = 0.8, leg.round = 2, leg.wid = 4, leg.just = "right", cex.scale = 0.8, xf = 9000, logscale = TRUE, accentuate = FALSE)
X |
X-coordinates |
Y |
Y-coordinates |
z |
values on the coordinates |
type |
"percentile" for percentile legend, "boxplot" for boxplot legend |
qutiles |
considered quantiles if type="percentile" is used |
q |
if not NULL, provide manually data points where to break |
symbtype |
type of symbols to be used; "EDA", "EDAacc", "EDAacc2", "EDAext", "GSC" or "arbit" |
symbmagn |
magnification factor for symbols |
leg.position |
position of the legend, either character like "topright" or coordinates |
leg.title |
title for legend |
leg.title.cex |
cex for legend |
leg.round |
round legend to specified digits "pretty" |
leg.wid |
width (space in numbers) for legend |
leg.just |
how to justify the legend |
cex.scale |
cex for text "log-scale" and for boxplot legend - only for type="boxplot" |
xf |
x-distance from boxplot to number for legend |
logscale |
if TRUE a log scale is used (for boxplot scale) and the log-boxplot is computed |
accentuate |
if TRUE, accentuated symbols are used (here only EDA accentuated!) |
It is possible to choose between different methods for calculating the range of the values for the different symbols.
If type="percentile" the pre-determined quantiles of the data are computed and are used to plot the symbols. If type="boxplot" a boxplot is computed and the values were taken to group the values fot the plot and the legend. In the case that a log scale is used the function boxplotlog is used instead of boxplot.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(chorizon) data(kola.background) el=chorizon[,"As"] X=chorizon[,"XCOO"] Y=chorizon[,"YCOO"] plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n") plotbg(map.col=c("gray","gray","gray","gray"),add.plot=TRUE) SymbLegend(X,Y,el,type="percentile",qutiles<-c(0,0.05,0.25,0.75,0.95,1),symbtype="EDA", symbmagn=0.8,leg.position="topright",leg.title="As [mg/kg]",leg.title.cex=0.8,leg.round=2, leg.wid=4,leg.just="right")data(chorizon) data(kola.background) el=chorizon[,"As"] X=chorizon[,"XCOO"] Y=chorizon[,"YCOO"] plot(X,Y,frame.plot=FALSE,xaxt="n",yaxt="n",xlab="",ylab="",type="n") plotbg(map.col=c("gray","gray","gray","gray"),add.plot=TRUE) SymbLegend(X,Y,el,type="percentile",qutiles<-c(0,0.05,0.25,0.75,0.95,1),symbtype="EDA", symbmagn=0.8,leg.position="topright",leg.title="As [mg/kg]",leg.title.cex=0.8,leg.round=2, leg.wid=4,leg.just="right")
This plot shows the relative proportions of three variables in one diagramm. It is important that the proportion sum up to 100% and if the values of the variables are very different it is important to scale them to the same data range.
ternary(x, nam = NULL, grid = FALSE, ...)ternary(x, nam = NULL, grid = FALSE, ...)
x |
matrix with 3 columns |
nam |
names of the variables |
grid |
if TRUE the grid should be plotted |
... |
further graphical parameters, see par |
The relative proportion of each variable is computed and those points are plotted into the graphic.
No return value, creates a plot.
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
data(moss) x=moss[,c("Ni","Cu","Pb")] ternary(x,grid=TRUE,pch=3,cex=0.7,col=1)data(moss) x=moss[,c("Ni","Cu","Pb")] ternary(x,grid=TRUE,pch=3,cex=0.7,col=1)
These are time trends from the Kola Project data.
data(timetrend)data(timetrend)
A data frame with 96 observations on the following 47 variables.
DDa numeric vector
MMa numeric vector
YYa numeric vector
Yeara numeric vector
Catcha numeric vector
X.IDa numeric vector
Aga numeric vector
Ala numeric vector
Asa numeric vector
Ba numeric vector
Baa numeric vector
Bea numeric vector
Bia numeric vector
Cda numeric vector
Coa numeric vector
Cra numeric vector
Cua numeric vector
Fea numeric vector
Ka numeric vector
Lia numeric vector
Mna numeric vector
Moa numeric vector
Nia numeric vector
Pba numeric vector
Rba numeric vector
Sba numeric vector
Sea numeric vector
Sra numeric vector
Tha numeric vector
Tla numeric vector
Ua numeric vector
Va numeric vector
Zna numeric vector
Caa numeric vector
Mga numeric vector
Naa numeric vector
Pa numeric vector
Sa numeric vector
Sia numeric vector
PO4a numeric vector
Bra numeric vector
Cla numeric vector
Fa numeric vector
NO3a numeric vector
SO4a numeric vector
pHa numeric vector
ECa numeric vector
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
Kola Project (1993-1998)
Reimann C, ?yr?s M, Chekushin V, Bogatyrev I, Boyd R, Caritat P de, Dutter R, Finne TE, Halleraker JH, J?ger ?, Kashulina G, Lehto O, Niskavaara H, Pavlov V, R?is?nen ML, Strand T, Volden T. Environmental Geochemical Atlas of the Central Barents Region. NGU-GTK-CKE Special Publication, Geological Survey of Norway, Trondheim, Norway, 1998.
data(timetrend) str(timetrend)data(timetrend) str(timetrend)
The Kola Data were collected in the Kola Project (1993-1998, Geological Surveys of Finland (GTK) and Norway (NGU) and Central Kola Expedition (CKE), Russia). More than 600 samples in five different layers were analysed, this dataset contains the C-horizon.
data(topsoil)data(topsoil)
A data frame with 607 observations on the following 45 variables.
IDa numeric vector
XCOOa numeric vector
YCOOa numeric vector
ELEVa numeric vector
COUNa factor with levels FIN NOR RUS
ASPa factor with levels E FLAT N NE NW NW S SE SW W
TOPCa numeric vector
LITOa numeric vector
Ac_228a numeric vector
Asa numeric vector
Aua numeric vector
Baa numeric vector
Bi_214a numeric vector
Bra numeric vector
Caa numeric vector
Cea numeric vector
Coa numeric vector
Cra numeric vector
Csa numeric vector
Cs_137a numeric vector
ECa numeric vector
Eua numeric vector
Fea numeric vector
Hfa numeric vector
Hga numeric vector
K_40a numeric vector
Laa numeric vector
LOIa numeric vector
Lua numeric vector
Moa numeric vector
Naa numeric vector
Nda numeric vector
Nia numeric vector
pHa numeric vector
Rba numeric vector
Sba numeric vector
Sca numeric vector
Sma numeric vector
Sra numeric vector
Tba numeric vector
Tha numeric vector
Ua numeric vector
Wa numeric vector
Yba numeric vector
Zna numeric vector
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
Kola Project (1993-1998)
Reimann C, ?yr?s M, Chekushin V, Bogatyrev I, Boyd R, Caritat P de, Dutter R, Finne TE, Halleraker JH, J?ger ?, Kashulina G, Lehto O, Niskavaara H, Pavlov V, R?is?nen ML, Strand T, Volden T. Environmental Geochemical Atlas of the Central Barents Region. NGU-GTK-CKE Special Publication, Geological Survey of Norway, Trondheim, Norway, 1998.
data(topsoil) str(topsoil)data(topsoil) str(topsoil)
This function estimates the variance components for ANOVA.
varcomp(a1, a2, f1, f2)varcomp(a1, a2, f1, f2)
a1, a2
|
analytical duplicates |
f1, f2
|
field duplicates |
pct.regional |
percentage of regional variability |
pct.site |
percentage at site variability |
pct.analytical |
percentage of analytical variability |
pval |
p-value |
Peter Filzmoser <[email protected]> http://cstat.tuwien.ac.at/filz/
C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.
# field duplicates: data(CHorFieldDUP) xfield1=CHorFieldDUP[,5:98] xfield2=CHorFieldDUP[,99:192] # anaytical duplicates: data(CHorANADUP) xanal1=CHorANADUP[,3:96] xanal2=CHorANADUP[,97:190] varcomp(xanal1[,1],xanal2[,1],xfield1[,1],xfield2[,1])# field duplicates: data(CHorFieldDUP) xfield1=CHorFieldDUP[,5:98] xfield2=CHorFieldDUP[,99:192] # anaytical duplicates: data(CHorANADUP) xanal1=CHorANADUP[,3:96] xanal2=CHorANADUP[,97:190] varcomp(xanal1[,1],xanal2[,1],xfield1[,1],xfield2[,1])