Type:	Package
Title:	Multivariate Morphometric Analysis
Version:	1.0.2.1
Date:	2024-10-01
Maintainer:	Marek Šlenker <marek.slenker@savba.sk>
Description:	Tools for multivariate analyses of morphological data, wrapped in one package, to make the workflow convenient and fast. Statistical and graphical tools provide a comprehensive framework for checking and manipulating input data, statistical analyses, and visualization of results. Several methods are provided for the analysis of raw data, to make the dataset ready for downstream analyses. Integrated statistical methods include hierarchical classification, principal component analysis, principal coordinates analysis, non-metric multidimensional scaling, and multiple discriminant analyses: canonical, stepwise, and classificatory (linear, quadratic, and the non-parametric k nearest neighbours). The philosophy of the package is described in Šlenker et al. 2022.
URL:	https://github.com/MarekSlenker/MorphoTools2
BugReports:	https://github.com/MarekSlenker/MorphoTools2/issues
Depends:	R (≥ 2.10)
License:	GPL-3
Encoding:	UTF-8
LazyData:	true
RoxygenNote:	7.3.2
Imports:	ade4, candisc, car, class, ellipse, heplots, MASS, methods, plot3D, StatMatch, utils, vegan, stats
Suggests:	testthat, knitr, rmarkdown
VignetteBuilder:	knitr
NeedsCompilation:	no
Packaged:	2024-09-30 08:20:10 UTC; mint
Author:	Marek Šlenker [aut, cre], Petr Koutecký [ctb], Karol Marhold [ctb]
Repository:	CRAN
Date/Publication:	2024-10-02 12:10:02 UTC

Box's M-test for Homogeneity of Covariance Matrices

Description

The boxMTest function performs Box's (1949) M-test for homogeneity of covariance matrices. The null hypothesis for this test is that the observed covariance matrices for the dependent variables are equal across groups.

Usage

boxMTest(object)

Arguments

Value

None. Used for its side effect.

References

Box G.E.P. (1949). A general distribution theory for a class of likelihood criteria. Biometrika 36, 317-346.

Examples

data(centaurea)

# remove NAs and linearly dependent characters (characters with unique contributions
#                  can be identified by stepwise discriminant analysis.)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))
centaurea = keepCharacter(centaurea, c("MLW", "ML", "IW", "LS", "IV", "MW", "MF",
                                    "AP", "IS", "LBA", "LW", "AL", "ILW", "LBS",
                                    "SFT", "CG", "IL", "LM", "ALW", "AW", "SF") )
# add a small constant to characters witch are invariant within taxa
centaurea$data[ centaurea$Taxon == "hybr", "LM" ][1] =
             centaurea$data[ centaurea$Taxon == "hybr", "LM" ][1] + 0.000001
centaurea$data[ centaurea$Taxon == "ph", "IV" ][1] =
             centaurea$data[ centaurea$Taxon == "ph", "IV" ][1] + 0.000001
centaurea$data[ centaurea$Taxon == "st", "LBS"][1] =
             centaurea$data[ centaurea$Taxon == "st", "LBS"][1] + 0.000001

boxMTest(centaurea)

Box Plots

Description

These functions produce a box-and-whisker plot(s) of the given morphological character(s).

Usage

boxplotCharacter(object, character, outliers = TRUE, lowerWhisker = 0.05,
          upperWhisker = 0.95, col = "white", border = "black", main = character,
          cex.main = 1.5, xlab = NULL, ylab = NULL, frame = TRUE, pch = 8,
          horizontal = FALSE, varwidth = FALSE, ...)

boxplotAll(object, folderName = "boxplots", outliers = TRUE, lowerWhisker = 0.05,
      upperWhisker = 0.95, col = "white", border = "black", main = character,
      cex.main = 1.5, xlab = NULL, ylab = NULL, frame = TRUE, pch = 8,
      horizontal = FALSE, varwidth = FALSE, width = 480, height = 480, units = "px", ...)

Arguments

Details

These functions modify the classical boxplot function to allow whiskers to be extended to the desired percentiles. By default, the whiskers are extended to the 5th and 95th percentiles, because of the trimmed range (without the most extreme 10% of values) use to be used in taxa descriptions, determination keys, etc. Box defines 25th and 75th percentiles, bold horizontal line shows median (50th percentile). Missing values are ignored.

The boxplotAll function produces boxplots for each morphological character and saves them to a folder defined by the folderName argument. If it does not exist, a new folder is created.

Value

None. Used for its side effect of producing a plot(s).

Examples

data(centaurea)

boxplotCharacter(centaurea, character = "ST", col = "orange", border = "red")

boxplotCharacter(centaurea, character = "ST", outliers = FALSE,
          lowerWhisker = 0.1, upperWhisker = 0.9)

boxplotCharacter(centaurea, "ST", varwidth = TRUE, notch = TRUE,
          boxwex = 0.4, staplewex = 1.3, horizontal = TRUE)

boxplotCharacter(centaurea, "ST", boxlty = 1, medlwd = 5,
          whisklty = 2, whiskcol = "red", staplecol = "red",
          outcol = "grey30", pch = "-")

## Not run: boxplotAll(centaurea, folderName = "../boxplots")

Canonical Discriminant Analysis

Description

This function performs canonical discriminant analysis.

Usage

cda.calc(object, passiveSamples = NULL)

Arguments

Details

The cda.calc function performs canonical discriminant analysis using the candisc method from the candisc package. Canonical discriminant analysis finds linear combination of the quantitative variables that maximize the difference in the mean discriminant score between groups. This function allows exclude subset of samples (passiveSamples) from computing the discriminant function, and only passively predict them in multidimensional space. This approach is advantageous for testing the positions of “atypical” populations (e.g., putative hybrids) or for assessing positions of selected individuals (e.g., type herbarium specimens).

Value

an object of class cdadata with the following elements:

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

cdaRes = cda.calc(centaurea)

summary(cdaRes)

plotPoints(cdaRes, col = c("red", "green", "blue", "red"),
  pch = c(20, 17, 8, 21), pt.bg = "orange", legend = TRUE)

Class Cdadata

Description

The cdadata class is designed for storing results of canonical discriminant analysis.

Format

Class cdadata.

objects

ID

IDs of each row of scores object.

Population

population membership of each row of scores object.

Taxon

taxon membership of each row of scores object.

scores

ordination scores of cases (objects, OTUs).

eigenValues

eigenvalues, i.e., proportion of variation of the original dataset expressed by individual axes.

eigenvaluesAsPercent

eigenvalues as percent, percentage of their total sum.

cumulativePercentageOfEigenvalues

cumulative percentage of eigenvalues.

groupMeans

data.frame containing the means for the taxa.

rank

number of non-zero eigenvalues.

coeffs.raw

matrix containing the raw canonical coefficients.

coeffs.std

matrix containing the standardized canonical coefficients.

totalCanonicalStructure

matrix containing the total canonical structure coefficients, i.e., total-sample correlations between the original variables and the canonical variables.

canrsq

squared canonical correlations.

25 Morphological Characters of Three Species of the Centaurea phrygia Complex

Description

The sample data include part of data sets from previously published studies by Koutecky (2007) and Koutecky et al. (2012): 25 morphological characters (see the cited studies for details) of the vegetative (stems and leaves) and reproductive structures (capitula and achenes) of three diploid species of the Centaurea phrygia complex: C. phrygia L. s.str. (abbreviated “ph”), C. pseudophrygia C.A.Mey. (“ps”) and C. stenolepis A.Kern. (“st”). Moreover, a fourth group includes the putative hybrid of the C. pseudophrygia and C. stenolepis (“hybr”). The data represent 8, 12, 7 and 6 populations for each group, respectively, and 20 individuals per population, with one exception in which only 12 individuals were available. All morphological characters are either quantitative (sizes, counts, or ratios) or binary (two characters states or presence/absence). In four characters of achenes (AL, AW, ALW, AP), there are missing data because fruits were not available in all individuals. In two populations of C. stenolepis (LIP, PREL) fruits were completely missing. In total, the data set includes 652 individuals (453 complete) from 33 populations (31 complete).

Usage

data(centaurea)

Format

an object of class morphodata with the following elements:

References

Koutecky P. (2007). Morphological and ploidy level variation of Centaurea phrygia agg.(Asteraceae) in the Czech Republic, Slovakia and Ukraine. Folia Geobotanica 42, 77-102.
Koutecky P., Stepanek J., Badurova T. (2012). Differentiation between diploid and tetraploid Centaurea phrygia: mating barriers, morphology and geographic distribution. Preslia 84, 1-32.

List Morphological Characters

Description

Returns list morphological characters of object.

Usage

characters(object)

Arguments

Value

A character vector containing names of morphological characters of object.

Examples

data(centaurea)

characters(centaurea)

Classificatory Discriminant Analysis

Description

These functions computes discriminant function for classifying observations. Linear discriminant function (classif.lda), quadratic discriminant function (classif.qda), or nonparametric k-nearest neighbours classification method (classif.knn) can be used.

Usage

classif.lda(object, crossval = "indiv")

classif.qda(object, crossval = "indiv")

classif.knn(object, k, crossval = "indiv")

Arguments

Details

The classif.lda and classif.qda performs classification using linear and quadratic discriminant functions with cross-validation using the lda and qda functions from the package MASS. The prior probabilities of group memberships are equal.

LDA and QDA analyses have some requirements: (1) no character can be a linear combination of any other character; (2) no pair of characters can be highly correlated; (3) no character can be invariant in any taxon; (4) for the number of taxa (g), characters (p) and total number of samples (n) should hold: 0 < p < (n - g), and (5) there must be at least two groups (taxa), and in each group there must be at least two objects. Violation of some of these assumptions may result in warnings or error messages (rank deficiency).

Nonparametric classification method k-nearest neighbours is performed using the knn and knn.cv functions from the package class.

The mode of crossvalidation is set by the parameter crossval. The default "indiv" uses the standard one-leave-out method. However, as some hierarchical structure is usually present in the data (individuals from a population are not completely independent observations, as they are morphologically closer to each other than to individuals from other populations), the value "pop" sets whole populations as leave-out units. The latter method does not allow classification if there is only one population for a taxon and is more sensitive to “atypical” populations, which usually leads to a somewhat lower classification success rate.

The coefficients of the linear discriminant functions (above) can be directly applied to classify individuals of unknown group membership. The sums of constant and multiples of each character by the corresponding coefficient are compared among the groups. The unknown individual is classified into the group that shows the higher score. If the populations leave-out cross-validation mode is selected (crossval = "pop"): (1) each taxon must be represented by at least two populations; (2) coefficients of classification functions are computed as averages of coefficients retrieved after each run with one population removed.

Value

an object of class classifdata with the following elements:

See Also

classifSample.lda, classif.matrix, knn.select

Examples

data(centaurea)

# remove NAs and linearly dependent characters (characters with unique contributions
#                  can be identified by stepwise discriminant analysis.)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))
centaurea = keepCharacter(centaurea, c("MLW", "ML", "IW", "LS", "IV", "MW", "MF",
                                    "AP", "IS", "LBA", "LW", "AL", "ILW", "LBS",
                                    "SFT", "CG", "IL", "LM", "ALW", "AW", "SF") )
# add a small constant to characters witch are invariant within taxa
centaurea$data[ centaurea$Taxon == "hybr", "LM" ][1] =
             centaurea$data[ centaurea$Taxon == "hybr", "LM" ][1] + 0.000001
centaurea$data[ centaurea$Taxon == "ph", "IV" ][1] =
             centaurea$data[ centaurea$Taxon == "ph", "IV" ][1] + 0.000001
centaurea$data[ centaurea$Taxon == "st", "LBS"][1] =
             centaurea$data[ centaurea$Taxon == "st", "LBS"][1] + 0.000001



# classification by linear discriminant function
classifRes.lda = classif.lda(centaurea, crossval = "indiv")

# classification by quadratic discriminant function
classifRes.qda = classif.qda(centaurea, crossval = "indiv")

# classification by nonparametric k-nearest neighbour method
# use knn.select to find the optimal K.
knn.select(centaurea, crossval = "pop")
classifRes.knn = classif.knn(centaurea, k = 12, crossval = "pop")

# exporting results
classif.matrix(classifRes.lda, level = "taxon")
classif.matrix(classifRes.qda, level = "taxon")
classif.matrix(classifRes.knn, level = "taxon")

Format the Classifdata to Summary Table

Description

The classif.matrix method formats the results stored in classifdata class to a summary classification table of taxa, populations, or individuals.

Usage

classif.matrix(result, level = "taxon")

Arguments

Value

A data.frame, summary classification table.

Examples

data(centaurea)

centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

# classification by linear discriminant function
classifRes.lda = classif.lda(centaurea, crossval = "indiv")

# exporting results
classif.matrix(classifRes.lda, level = "taxon")
classif.matrix(classifRes.lda, level = "pop")

Classificatory Discriminant Analysis

Description

These functions compute discriminant function based on an independent training set and classify observations in sample set. Linear discriminant function (classifSample.lda), quadratic discriminant function (classifSample.qda), or nonparametric k-nearest neighbour classification method (classifSample.knn) can be used.

Usage

classifSample.lda(sampleData, trainingData)

classifSample.qda(sampleData, trainingData)

classifSample.knn(sampleData, trainingData, k)

Arguments

Details

The classifSample.lda and classifSample.qda performs classification using linear and quadratic discriminant function using the lda and qda functions from the package MASS. Nonparametric classification method classifSample.knn (k-nearest neighbours) is performed using the knn functions from the package class. The classifSample functions are designed to classify hybrid populations, type herbarium specimens, atypical samples, entirely new data, etc. Discriminant criterion is developed from the original (training) dataset and applied to the specific sample (set).

LDA and QDA analyses have some requirements: (1) no character can be a linear combination of any other character; (2) no pair of characters can be highly correlated; (3) no character can be invariant in any taxon (group); (4) for the number of taxa (g), characters (p) and total number of samples (n) should hold: 0 < p < (n - g), and (5) there must be at least two groups (taxa), and in each group there must be at least two objects. Violation of some of these assumptions may result in warnings or error messages (rank deficiency).

Value

an object of class classifdata with the following elements:

See Also

classif.lda, classif.matrix, knn.select

Examples

data(centaurea)

# remove NAs and linearly dependent characters (characters with unique contributions
#                  can be identified by stepwise discriminant analysis.)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))
centaurea = keepCharacter(centaurea, c("MLW", "ML", "IW", "LS", "IV", "MW", "MF",
                                    "AP", "IS", "LBA", "LW", "AL", "ILW", "LBS",
                                    "SFT", "CG", "IL", "LM", "ALW", "AW", "SF") )
# add a small constant to characters witch are invariant within taxa
centaurea$data[ centaurea$Taxon == "hybr", "LM" ][1] =
             centaurea$data[ centaurea$Taxon == "hybr", "LM" ][1] + 0.000001
centaurea$data[ centaurea$Taxon == "ph", "IV" ][1] =
             centaurea$data[ centaurea$Taxon == "ph", "IV" ][1] + 0.000001
centaurea$data[ centaurea$Taxon == "st", "LBS"][1] =
             centaurea$data[ centaurea$Taxon == "st", "LBS"][1] + 0.000001


trainingSet = removePopulation(centaurea, populationName = "LES")
LES = keepPopulation(centaurea, populationName = "LES")


# classification by linear discriminant function
classifSample.lda(LES, trainingSet)

# classification by quadratic discriminant function
classifSample.qda(LES, trainingSet)

# classification by nonparametric k-nearest neighbour method
# use knn.select to find the optimal K.
knn.select(trainingSet)
classifSample.knn(LES, trainingSet, k = 12)

Class classifdata

Description

The classifdata class is designed for storing results of classificatory discriminant analysis.

Format

Class classifdata.

ID

IDs of each row.

Population

population membership of each row.

Taxon

taxon membership of each row.

classif

classification from discriminant analysis.

classif.funs

the classification functions computed for raw characters (descriptors). If crossval = "pop", means of coefficients of classification functions are computed.

prob

posterior probabilities of classification into each taxon (if calculated by classif.lda or classif.qda), or proportion of the votes for the winning class (calculated by classif.knn)

correct

logical, correctness of classification.

Hierarchical Clustering

Description

Hierarchical cluster analysis of objects.

Usage

clust(object, distMethod = "Euclidean", clustMethod = "UPGMA", binaryChs = NULL,
              nominalChs = NULL, ordinalChs = NULL)

Arguments

Details

This function performs agglomerative hierarchical clustering. Typically, populations are used as OTUs (operational taxonomic units). Characters are standardised to a zero mean and a unit standard deviation.

Various measures of distance between the observations (rows) are applicable: (1) coefficients of distance for quantitative and binary characters: "Euclidean", "Manhattan", "Minkowski"; (2) similarity coefficients for binary characters: "Jaccard" and simple matching ("simpleMatching"); (3) coefficient for mixed data: "Gower". Note that the other than default methods for clustering and distance measurement are rarely used in morphometric analyses.

The Gower's dissimilarity coefficient can handle different types of variables. Characters have to be divided into four categories: (1) quantitative characters, (2) categorical ordinal characters, (3) categorical nominal (multistate) characters, and (4) binary characters. All characters are considered to be quantitative characters unless otherwise specified. Other types of characters have to be explicitly specified. To mark characters as ordinal, nominal, or binary, enumerate them by names using ordinalChs, nominalChs, and binaryChs arguments, respectively.

Value

An object of class 'hclust'. It encodes a stepwise dendrogram.

Examples

data(centaurea)

clustering.UPGMA = clust(centaurea)

plot(clustering.UPGMA, cex = 0.6, frame.plot = TRUE, hang = -1,
        main = "", sub = "", xlab = "", ylab = "distance")


# using Gower's method
data = list(
    ID = as.factor(c("id1","id2","id3","id4","id5","id6")),
    Population = as.factor(c("Pop1", "Pop1", "Pop2", "Pop2", "Pop3", "Pop3")),
    Taxon = as.factor(c("TaxA", "TaxA", "TaxA", "TaxB", "TaxB", "TaxB")),
    data = data.frame(
     stemBranching = c(1, 1, 1, 0, 0, 0),  # binaryChs
     petalColour = c(1, 1, 2, 3, 3, 3),  # nominalChs; 1=white, 2=red, 3=blue
     leaves = c(1,1,1,2,2,3), # nominalChs; 1=simple, 2=palmately compound, 3=pinnately compound
     taste = c(2, 2, 2, 3, 1, 1),   # ordinal; 1=hot, 2=hotter, 3=hottest
     stemHeight = c(10, 11, 14, 22, 23, 21),         # quantitative
     leafLength = c(8, 7.1, 9.4, 1.2, 2.3, 2.1)  )   # quantitative
)
attr(data, "class") = "morphodata"

clustering.GOWER = clust(data, distMethod = "Gower", clustMethod = "UPGMA",
                               binaryChs = c("stemBranching"),
                               nominalChs = c("petalColour", "leaves"),
                               ordinalChs = c("taste"))

plot(clustering.GOWER, cex = 0.6, frame.plot = TRUE, hang = -1,
        main = "", sub = "", xlab = "", ylab = "distance")

Correlations of Characters

Description

The cormat function calculates the matrix of the correlation coefficients of the characters.

Usage

cormat(object, method = "Pearson")

cormatSignifTest(object, method = "Pearson", alternative = "two.sided")

Arguments

Details

This function returns table with pairwise correlation coefficients for each pair of morphological characters. The result is formatted as a data.frame to allow export with the exportRes function.

Significance tests are usually unnecessary for morphometric analysis. Anyway, if tests are needed, they can be computed using the cormatSignifTest function.

Value

A data.frame, storing correlation coefficients for each pair of morphological characters.

Examples

data(centaurea)

correlations.p = cormat(centaurea, method = "Pearson")
correlations.s = cormat(centaurea, method = "Spearman")

## Not run: exportRes(correlations.p, file = "correlations.pearson.txt")
## Not run: exportRes(correlations.s, file = "correlations.spearman.txt")

correlations.p = cormatSignifTest(centaurea, method = "Pearson")

Descriptive Statistics

Description

These functions calculate the descriptive statistics of each character in the whole dataset, each taxon and each population.

Usage

descrTaxon(object, format = NULL, decimalPlaces = 3)

descrPopulation(object, format = NULL, decimalPlaces = 3)

descrAll(object, format = NULL, decimalPlaces = 3)

Arguments

Details

The following statistics are computed: number of observations, mean, standard deviation, and the percentiles: 0% (minimum), 5%, 25% (lower quartile), 50% (median), 75% (upper quartile), 95% and 100% (maximum).

The format argument brings a handy way how to receive only what is wanted and in format what is desired. Otherways, if format remains NULL, output table contains all calculated descriptors. The format argument is a single string, where keywords will be replaced by particular values.

Keywords: "$MEAN" = mean; "$SD" = standard deviation; "$MIN" = minimum; "$5%" = 5th percentile; "$25%" = 25th percentile (lower quartile); "$MEDIAN" = median (50th percentile); "$75%" = 75th percentile (upper quartile); "$95%" = 95th percentile; "$MAX" = maximum.

Value

A data.frame with calculated statistical descriptors.

Examples

data(centaurea, decimalPlaces = 3)

descrTaxon(centaurea)

descrTaxon(centaurea, format = "($MEAN ± $SD)")

descrPopulation(centaurea, format = "$MEAN ($MIN - $MAX)")

descrAll(centaurea, format = "$MEAN ± $SD ($5% - $95%)")

Export Data

Description

This function is designed for exporting results, stored in objects of MorphoTools2 package.

Usage

exportRes(object, file = "", dec = ".", sep = "\t",
          row.names = FALSE, col.names = TRUE)

Arguments

Value

None. Used for its side effect.

Examples

data(centaurea)

descr = descrTaxon(centaurea, format = "($MEAN ± $SD)")
## Not run: exportRes(descr, file = "centaurea_descrTax.txt")

Return the First or Last Parts of an Object

Description

Returns the first or last parts of a object.

Usage

## S3 method for class 'classifdata'
head(x, n = 6, ...)

## S3 method for class 'classifdata'
tail(x, n = 6, ...)

## S3 method for class 'morphodata'
head(x, n = 6, ...)

## S3 method for class 'morphodata'
tail(x, n = 6, ...)

Arguments

Details

Object passed as parameter is formated to data.frame. A head() (tail()) returns the first (last) n rows when n >= 0 or all but the last (first) n rows when n < 0.

Value

A data.frame, containing the first or last n individuals of the passed object.

Examples

data(centaurea)

head(centaurea)
tail(centaurea)

Histograms of Characters

Description

Histograms are produced for the level of taxa/groups, to displays a within-group distribution of each taxon for a particular character, and its deviation from the normal distribution (red line).

Usage

histCharacter(object, character, taxon = levels(object$Taxon), histogram = TRUE,
        col = "lightgray", main = NULL, densityLine = TRUE, normDistLine = TRUE, ...)

histAll(object, folderName = "histograms", taxon = levels(object$Taxon),
		histogram = TRUE, col = "lightgray", main = NULL, densityLine = TRUE,
		normDistLine = TRUE, width = 480, height = 480, units = "px", ...)

Arguments

Value

None. Used for its side effect of producing a plot(s).

Examples

data(centaurea)

histCharacter(centaurea, character = "IW", breaks = seq(0.5, 2.5, 0.1))

## Not run: histAll(centaurea, folderName = "../histograms")

Keep Items (Taxa, Populations, Samples, Morphological Characters) in an Morphodata Object (and Remove Others)

Description

These functions keep only selected taxa, populations, samples or morphological characters in morphodata object. The samples can be kept by names using sampleName argument, or by the threshold. Each sample holding less or equal portion of missing data than the desired threshold (missingPercentage) will be kept. Only one parameter can be specified in one run.

Usage

keepTaxon(object, taxonName)

keepPopulation(object, populationName)

keepSample(object, sampleName = NULL, missingPercentage = NA)

keepCharacter(object, characterName)

Arguments

Value

an object of class morphodata with the following elements:

Examples

data(centaurea)

centaurea.hybr = keepTaxon(centaurea, "hybr")
centaurea.PhHybr = keepTaxon(centaurea, c("ph", "hybr"))

centaurea.PREL = keepPopulation(centaurea, "PREL")

centaurea.NA_0.1 = keepSample(centaurea, missingPercentage = 0.1)

centaurea.stem = keepCharacter(centaurea, c("SN", "SF", "ST"))

Search for the Optimal K-nearest Neighbours

Description

This function search for the optimal number of neighbours for the given data set for k-nearest neighbour cross-validatory classification.

Usage

knn.select(object, crossval = "indiv")

Arguments

Details

The knn.select function compute number of correctly classified individuals for k values ranging from 1 to 30 and highlight the value with the highest success rate. Ties (i.e., when there are the same numbers of votes for two or more groups) are broken at random, and thus several iterations may yield different results. Therefore, the functions compute 10 iterations, and the average success rates for each k are used; the minimum and maximum success rates for each k are also displayed as error bars. Note that several k values may have nearly the same success rates; if this is the case, the similarity of iterations may also be considered.

The mode of crossvalidation is set by the parameter crossval. The default "indiv" uses the standard one-leave-out method. However, as some hierarchical structure is usually present in the data (individuals from a population are not completely independent observations, as they are morphologically closer to each other than to individuals from other populations), the value "pop" sets whole populations as leave-out units. The latter method does not allow classification if there is only one population for a taxon and is more sensitive to “atypical” populations, which usually leads to a somewhat lower classification success rate.

Value

Optimal number of neighbours is written to the console, and plot displaying all Ks is produced.

See Also

classif.lda, classifSample.lda, classif.qda, classifSample.qda, classif.knn, classifSample.knn

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

# classification by nonparametric k-nearest neighbour method
knn.select(centaurea, crossval = "indiv")
classifRes.knn = classif.knn(centaurea, k = 12, crossval = "indiv")

Summarize Missing Data

Description

Summarize percentage and number of missing values on the desired grouping level.

Usage

missingCharactersTable(object, level)

Arguments

Value

A data.frame summarizing a number of missing values.

Examples

data(centaurea)

missingCharactersTable(centaurea, level = "pop")

Summarize Missing Data

Description

Summarize number of missing values for each character on the desired grouping level.

Usage

missingSamplesTable(object, level)

Arguments

Value

A data.frame summarizing a number of missing values.

Examples

data(centaurea)

missingSamplesTable(centaurea, level = "pop")

Class morphodata

Description

The morphodata class is designed for storing morphological data of individuals, their IDs and it's appertaining to population and taxon.

Format

Class morphodata.

ID

IDs of each row of data object.

Population

population membership of each row of data object.

Taxon

taxon membership of each row of data object.

data

data.frame of individuals (rows) and values of measured morphological characters (columns).

Replace Missing Data by Population Average

Description

This function substitutes missing data using the average value of the respective character in the respective population.

Usage

naMeanSubst(object)

Arguments

Details

Generally, most of the multivariate analyses require a full data matrix. The preferred approach is to reduce the data set to complete observations only (i.e., perform the casewise deletion of missing data) or to remove characters for which there are missing values. The use of mean substitution, which introduces values that are not present in the original data, is justified only if (1) there are relatively few missing values, (2) these missing values are scattered throughout many characters (each character includes only a few missing values) and (3) removing all individuals or all characters with missing data would unacceptably reduce the data set.

Value

an object of class morphodata with the following elements:

Examples

data(centaurea)

centaurea = naMeanSubst(centaurea)

Non-metric Multidimensional Scaling (NMDS)

Description

This function performs Non-metric multidimensional scaling.

Usage

nmds.calc(object, distMethod = "Euclidean", k = 3, binaryChs = NULL,
                    nominalChs = NULL, ordinalChs = NULL)

Arguments

Details

The nmds.calc function performs non-metric multidimensional scaling using the monoMDS function from package vegan. The main threat of NMDS is, that this method doesn't preserve distances among objects in the original character space and approximates only the order of the dissimilarities among objects, based on any coefficient of similarity or distance.

Further, multiple runs of the NMDS analysis are needed to ensure that the stable ordination has been reached, as anyone run may get “trapped” in local optima which are not representative of true similarities.

The stress value reflects how well the ordination summarizes the observed relationship among the samples. A rule of thumb, 0.1-0.2 is considered fairly good, but there is no general rule since the stress is greatly influenced by the number of points. Since stress decreases as dimensionality increases, the optimal solution is when the decrease in stress is small after decreasing the number of dimensions.

Various measures of distance between the observations (rows) are applicable: (1) coefficients of distance for quantitative and binary characters: "Euclidean", "Manhattan", "Minkowski"; (2) similarity coefficients for binary characters: "Jaccard" and simple matching ("simpleMatching"); (3) coefficient for mixed data: ("Gower").

The Gower's dissimilarity coefficient can handle different types of variables. Characters have to be divided into four categories: (1) quantitative characters, (2) categorical ordinal characters, (3) categorical nominal (multistate) characters, and (4) binary characters. All characters are considered to be quantitative characters unless otherwise specified. Other types of characters have to be explicitly specified. To mark characters as ordinal, nominal, or binary, enumerate them by names using ordinalChs, nominalChs, and binaryChs arguments, respectively.

Value

an object of class nmdsdata with the following elements:

Examples

data(centaurea)

nmdsRes = nmds.calc(centaurea, distMethod = "Euclidean", k = 3)

summary(nmdsRes)

plotPoints(nmdsRes, axes = c(1,2), col = c("red", "green", "blue", "black"),
  pch = c(20,17,8,21), pt.bg = "orange", legend = TRUE, legend.pos = "bottomright")

# using Gower's method
data = list(
    ID = as.factor(c("id1","id2","id3","id4","id5","id6")),
    Population = as.factor(c("Pop1", "Pop1", "Pop2", "Pop2", "Pop3", "Pop3")),
    Taxon = as.factor(c("TaxA", "TaxA", "TaxA", "TaxB", "TaxB", "TaxB")),
    data = data.frame(
     stemBranching = c(1, 1, 1, 0, 0, 0),  # binaryChs
     petalColour = c(1, 1, 2, 3, 3, 3),  # nominalChs; 1=white, 2=red, 3=blue
     leaves = c(1,1,1,2,2,3), # nominalChs; 1=simple, 2=palmately compound, 3=pinnately compound
     taste = c(2, 2, 2, 3, 1, 1),   # ordinal; 1=hot, 2=hotter, 3=hottest
     stemHeight = c(10, 11, 14, 22, 23, 21),         # quantitative
     leafLength = c(8, 7.1, 9.4, 1.2, 2.3, 2.1)  )   # quantitative
)
attr(data, "class") = "morphodata"

nmdsGower = nmds.calc(data, distMethod = "Gower", k = 2, binaryChs = c("stemBranching"),
                      nominalChs = c("petalColour", "leaves"), ordinalChs = c("taste"))

plotPoints(nmdsGower, axes = c(1,2), col = c("red","green"),
           pch = c(20,17), pt.bg = "orange", legend = TRUE, legend.pos = "bottomright")

Class nmdsdata

Description

The nmdsdata class is designed for storing results of non-metric multidimensional scaling (NMDS).

Format

Class nmdsdata.

objects

ID

IDs of each row of scores object.

Population

population membership of each row of scores object.

Taxon

taxon membership of each row of scores object.

scores

ordination scores of cases (objects, OTUs).

stress

stress value, e.i., goodness of fit.

groupMeans

data.frame containing the means for the taxa.

distMethod

used distance measure.

rank

number of possitive eigenvalues.

Principal Component Analysis

Description

This function performs principal component analysis.

Usage

pca.calc(object)

Arguments

Details

The pca.calc function performs an R type principal component analysis using the R base princomp function. Principal component analysis is a variable reduction procedure. It reduces original variables into a smaller number of principal components (artificial variables) that will account for most of the variance in the observed variables.

Value

an object of class pcadata with the following elements:

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

pcaRes = pca.calc(centaurea)

summary(pcaRes)

plotPoints(pcaRes, axes = c(1,2), col = c("red", "green", "blue", "black"),
  pch = c(20,17,8,21), pt.bg = "orange", legend = TRUE, legend.pos = "bottomright")

Class pcadata

Description

The pcadata class is designed for storing results of principal component analysis (PCA).

Format

Class pcadata.

objects

ID

IDs of each row of scores object.

Population

population membership of each row of scores object.

Taxon

taxon membership of each row of scores object.

scores

ordination scores of cases (objects, OTUs).

eigenVectors

matrix of eigenvectors (i.e., a matrix of characters loadings).

eigenValues

eigenvalues of principal components, i.e., proportion of variation of the original dataset expressed by individual axes.

eigenvaluesAsPercent

eigenvalues as percent, percentage of their total sum.

cumulativePercentageOfEigenvalues

cumulative percentage of eigenvalues.

groupMeans

data.frame containing the means for the taxa.

rank

number of principal components.

center, scale

the centring and scaling of the input data.

Principal Coordinates Analysis (PCoA)

Description

This function performs principal coordinates analysis.

Usage

pcoa.calc(object, distMethod = "Euclidean", binaryChs = NULL,
               nominalChs = NULL, ordinalChs = NULL)

Arguments

Details

The pcoa.calc function performs principal coordinates analysis using the cmdscale function from package stats. Principal coordinates analysis estimates coordinates for a set of objects in a space. Distances among objects is approximationy of the dissimilarities, based on any similarity or distance coefficient.

Various measures of distance between the observations (rows) are applicable: (1) coefficients of distance for quantitative and binary characters: "Euclidean", "Manhattan", "Minkowski"; (2) similarity coefficients for binary characters: "Jaccard" and simple matching ("simpleMatching"); (3) coefficient for mixed data: ("Gower").

The Gower's dissimilarity coefficient can handle different types of variables. Characters have to be divided into four categories: (1) quantitative characters, (2) categorical ordinal characters, (3) categorical nominal (multistate) characters, and (4) binary characters. All characters are considered to be quantitative characters unless otherwise specified. Other types of characters have to be explicitly specified. To mark characters as ordinal, nominal, or binary, enumerate them by names using ordinalChs, nominalChs, and binaryChs arguments, respectively.

Value

an object of class pcoadata with the following elements:

Examples

data(centaurea)

pcoRes = pcoa.calc(centaurea, distMethod = "Manhattan")

summary(pcoRes)

plotPoints(pcoRes, axes = c(1,2), col = c("red", "green", "blue", "black"),
  pch = c(20,17,8,21), pt.bg = "orange", legend = TRUE, legend.pos = "bottomright")

# using Gower's method
data = list(
    ID = as.factor(c("id1","id2","id3","id4","id5","id6")),
    Population = as.factor(c("Pop1", "Pop1", "Pop2", "Pop2", "Pop3", "Pop3")),
    Taxon = as.factor(c("TaxA", "TaxA", "TaxA", "TaxB", "TaxB", "TaxB")),
    data = data.frame(
     stemBranching = c(1, 1, 1, 0, 0, 0),  # binaryChs
     petalColour = c(1, 1, 2, 3, 3, 3),  # nominalChs; 1=white, 2=red, 3=blue
     leaves = c(1,1,1,2,2,3), # nominalChs; 1=simple, 2=palmately compound, 3=pinnately compound
     taste = c(2, 2, 2, 3, 1, 1),   # ordinal; 1=hot, 2=hotter, 3=hottest
     stemHeight = c(10, 11, 14, 22, 23, 21),         # quantitative
     leafLength = c(8, 7.1, 9.4, 1.2, 2.3, 2.1)  )   # quantitative
)
attr(data, "class") = "morphodata"

pcoaGower = pcoa.calc(data, distMethod = "Gower", binaryChs = c("stemBranching"),
                      nominalChs = c("petalColour", "leaves"), ordinalChs = c("taste"))

plotPoints(pcoaGower, axes = c(1,2), col = c("red","green"),
           pch = c(20,17), pt.bg = "orange", legend = TRUE, legend.pos = "bottomright")

Class pcoadata

Description

The pcoadata class is designed for storing results of principal coordinates analysis (PCoA).

Format

Class pcoadata.

objects

ID

IDs of each row of scores object.

Population

population membership of each row of scores object.

Taxon

taxon membership of each row of scores object.

scores

ordination scores of cases (objects, OTUs).

eigenValues

eigenvalues of principal coordinates.

eigenvaluesAsPercent

eigenvalues as percent, percentage of their total sum.

cumulativePercentageOfEigenvalues

cumulative percentage of eigenvalues.

groupMeans

data.frame containing the means for the taxa.

distMethod

used distance measure.

rank

number of possitive eigenvalues.

The Default Scatterplot 3D Function

Description

A generic function for plotting ordination scores stored in pcadata, pcoadata, nmdsdata, and cdadata objects.

Usage

plot3Dpoints(result, axes = c(1,2,3), xlab = NULL, ylab = NULL, zlab = NULL,
  pch = 16, col = "black", pt.bg = "white", phi = 10, theta = 2,
  ticktype = "detailed", bty = "u", type = "p", labels = FALSE,
 legend = FALSE, legend.pos = "topright", ncol = 1, ...)

Arguments

Value

None. Used for its side effect of producing a plot.

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

pcaRes = pca.calc(centaurea)

plot3Dpoints(pcaRes, col = c("red", "green", "blue", "black"), pch = c(20,17,8,21),
                 pt.bg = "orange")

Add Prediction Ellipses to a Plot

Description

This function draws prediction ellipses around taxa.

Usage

plotAddEllipses(result, axes = c(1,2), probability = 0.95, col = "black",
                  type = "l", lty = 1, lwd = 1, ...)

Arguments

Details

Prediction ellipses with given probability define the regions where will fall any new independent observation from the respective taxa. The prediction ellipses are quantified using covariance matrices of taxa scores and chi-squared distribution with two degrees of freedom (Friendly et al. 2013).

Value

None. Used for its side effect of adding elements to a plot.

References

Friendly M., Monette G., Fox J. (2013). Elliptical insights: understanding statistical methods through elliptical geometry. Statistical Science 28, 1-39.

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

pcaRes = pca.calc(centaurea)

plotPoints(pcaRes, col = c(rgb(255, 0, 0, max = 255, alpha = 150), # red
                           rgb(0, 255, 0, max = 255, alpha = 150), # green
                           rgb(0, 0, 255, max = 255, alpha = 150), # blue
                           rgb(0, 0, 0, max = 255, alpha = 150)), # black
            legend = FALSE, xlim = c(-5, 7.5), ylim = c(-5, 5.5))

plotAddLegend(pcaRes, col = c("red", "green", "blue", "black"), ncol = 2)

plotAddEllipses(pcaRes, col = c("red", "green", "blue", "black"), lwd = 3)

Add Labels to a Plot

Description

This is a generic function for drawing labels to the character arrows of pcadata and cdadata objects.

Usage

plotAddLabels.characters(result, labels = characters(result), include = TRUE,
   axes = c(1,2), pos = NULL, offset = 0.5, cex = 0.7, col = NULL, breaks = 1, ...)

Arguments

Value

None. Used for its side effect of adding elements to a plot.

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))


pcaRes = pca.calc(centaurea)

plotCharacters(pcaRes, labels = FALSE)
plotAddLabels.characters(pcaRes, labels = c("MW", "IW", "SFT", "SF", "LW"), pos = 2, cex = 1)
plotAddLabels.characters(pcaRes, labels = c("LLW", "ILW", "LBA"), pos = 4, cex = 1)
plotAddLabels.characters(pcaRes, labels = c("ML", "IV", "MLW"), pos = 1, cex = 1)

Add Labels to a Plot

Description

This is a generic function for drawing labels to the data points of pcadata, pcoadata, nmdsdata, and cdadata objects.

Usage

plotAddLabels.points(result, labels = result$objects$ID, include = TRUE,
      axes = c(1,2), pos = NULL, offset = 0.5, cex = 1, col = NULL, ...)

Arguments

Value

None. Used for its side effect of adding elements to a plot.

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))
pops = populOTU(centaurea)


pcaRes = pca.calc(pops)
plotPoints(pcaRes, col = c("red", "green", "blue", "red"),
            pch = c(20, 17, 8, 21), pt.bg = "orange", legend = FALSE)

plotAddLabels.points(pcaRes, labels = c("LES", "BUK", "VOL", "OLE1"), include = TRUE)

plotPoints(pcaRes, col = c("red", "green", "blue", "red"),
            pch = c(20, 17, 8, 21), pt.bg = "orange", legend = FALSE)

plotAddLabels.points(pcaRes, labels = c("LES", "BUK", "VOL", "OLE1"), include = FALSE)

Add Legend to a Plot

Description

This function can be used to add legend to plot.

Usage

plotAddLegend(result, x = "topright", y = NULL, pch = 16, col = "black",
    pt.bg = "white", pt.cex = cex, pt.lwd = 1, x.intersp = 1,
    y.intersp = 1, box.type = "o", box.lty = "solid", box.lwd = 1,
    box.col = "black", box.bg = "white", cex = 1, ncol = 1, horiz = FALSE, ...)

Arguments

Value

None. Used for its side effect of adding elements to a plot.

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

pcaRes = pca.calc(centaurea)

plotPoints(pcaRes, col = c("red", "green", "blue", "red"),
            pch = c(20, 17, 8, 21), pt.bg = "orange", legend = FALSE)

plotAddLegend(pcaRes, x = "bottomright", col = c("red", "green", "blue", "red"),
               pch = c(20, 17, 8, 21), pt.bg = "orange", ncol = 2)

Add Spiders to a Plot

Description

This function connects taxa's points with its centroids, thus forms a “spider” diagram.

Usage

plotAddSpiders(result, axes = c(1,2), col = "black", lty = 1, lwd = 1, ...)

Arguments

Value

None. Used for its side effect of adding elements to a plot.

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

pcaRes = pca.calc(centaurea)

plotPoints(pcaRes, col = c(rgb(255, 0, 0, max = 255, alpha = 150), # red
                           rgb(0, 255, 0, max = 255, alpha = 150), # green
                           rgb(0, 0, 255, max = 255, alpha = 150), # blue
                           rgb(0, 0, 0, max = 255, alpha = 150)), # black
            legend = FALSE, xlim = c(-5, 7.5), ylim = c(-5, 5.5))

plotAddLegend(pcaRes, col = c("red", "green", "blue", "black"), ncol = 2)

plotAddSpiders(pcaRes, col = c("red", "green", "blue", "black"))


plotPoints(pcaRes, col = c("red", "green", "blue","black"), legend = TRUE, cex = 0.4)

plotAddSpiders(pcaRes, col = c(rgb(255, 0, 0, max = 255, alpha = 150), # red
                               rgb(0, 255, 0, max = 255, alpha = 150), # green
                               rgb(0, 0, 255, max = 255, alpha = 150), # blue
                               rgb(0, 0, 0, max = 255, alpha = 150))) # black

The Default Biplot Function

Description

A generic function for plotting ordination scores and the character's contribution to ordination axes in a single plot.

Usage

plotBiplot(result, axes = c(1,2), xlab = NULL, ylab = NULL,
      pch = 16, col = "black", pt.bg = "white", breaks = 1,
      xlim = NULL, ylim = NULL, labels = FALSE, arrowLabels = TRUE,
      colArrowLabels = "black", angle = 15, length = 0.1, arrowCol = "red",
      legend = FALSE, legend.pos = "topright", ncol = 1, ...)

Arguments

Details

This generic method holds separate implementations of plotting biplots for pcadata, and cdadata objects. If only one axis exists, sample scores are displayed as a histogram.

Value

None. Used for its side effect of producing a plot.

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

pcaRes = pca.calc(centaurea)

plotBiplot(pcaRes, axes = c(1,2), col = c("red", "green", "blue", "red"),
  pch = c(20, 17, 8, 21), pt.bg = "orange", legend = TRUE, legend.pos = "bottomright")

plotBiplot(pcaRes, main = "My PCA plot", cex = 0.8)

cdaRes = cda.calc(centaurea)

plotBiplot(cdaRes, col = c("red", "green", "blue", "red"),
  pch = c(20, 17, 8, 21), pt.bg = "orange", legend = TRUE)

Draws Character's Contribution as Arrows

Description

The character's contribution to ordination axes are visualised as arrows.

Usage

plotCharacters(result, axes = c(1, 2), xlab = NULL, ylab = NULL,
    main = NULL, xlim = NULL, ylim = NULL, col = "red", length = 0.1,
    angle = 15, labels = TRUE, cex = 0.7, ...)

Arguments

Details

The distribution of samples in ordination space is driven by morphological characters. Each character has its own contribution to ordination axes. These contributions are visualised as arrows. The direction and length of the arrows characterize the impact of the morphological characters on the separation of objects along a given axis. This information is stored in eigenvectors or total canonical structure coefficients for principal component analysis of canonical discriminant analysis, respectively.

The plotCharacters method is not applicable to results of the principal coordinates analysis (pcoa.calc) and non-metric multidimensional scaling (nmds.calc) analyses, as the influence of original characters on new axes can not be directly derived, and variation explained by individual axes is unknown.

Value

None. Used for its side effect of producing a plot.

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

pcaRes = pca.calc(centaurea)

plotCharacters(pcaRes)

The Default Scatterplot Function

Description

A generic function for plotting ordination scores stored in pcadata, pcoadata, nmdsdata, and cdadata objects.

Usage

plotPoints(result, axes = c(1,2), xlab = NULL, ylab = NULL,
      pch = 16, col = "black", pt.bg = "white", breaks = 1,
      ylim = NULL, xlim = NULL, labels = FALSE, legend = FALSE,
      legend.pos = "topright", ncol = 1, ...)

Arguments

Details

This generic method holds separate implementations of plotting points for pcadata, pcoadata, nmdsdata, and cdadata objects. If only one axis exists, sample scores are displayed as a histogram.

Value

None. Used for its side effect of producing a plot.

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

pcaRes = pca.calc(centaurea)

plotPoints(pcaRes, axes = c(1,2), col = c("red", "green", "blue", "red"),
  pch = c(20, 17, 8, 21), pt.bg = "orange", legend = TRUE, legend.pos = "bottomright")

plotPoints(pcaRes, main = "My PCA plot", cex = 0.8)

cdaRes = cda.calc(centaurea)

plotPoints(cdaRes, col = c("red", "green", "blue", "red"),
  pch = c(20, 17, 8, 21), pt.bg = "orange", legend = TRUE)

Population Means

Description

This function calculates the average value for each character in each population, with the pairwise deletion of missing data.

Usage

populOTU(object)

Arguments

Details

This function returns morphodata object, where each population is used as the operational taxonomic unit (OTUs), thus is represented by single “individual” (row) with average values for each character. Note that when using populations as OTUs, they are handled with the same weight in all analyses (disregarding population size, within-population variation, etc.)

Value

an object of class morphodata with the following elements:

Examples

data(centaurea)

pops = populOTU(centaurea)

Quantile-Quantile Plots

Description

Q-Q plots are produced for the level of taxa/groups, to displays a deviation of morphological characters of each taxon from the normal distribution (line).

Usage

qqnormCharacter(object, character, taxon = levels(object$Taxon), main = NULL, ...)

qqnormAll(object, folderName = "qqnormPlots", taxon = levels(object$Taxon),
          main = NULL, width = 480, height = 480, units = "px", ...)

Arguments

Value

None. Used for its side effect of producing a plot(s).

Examples

data(centaurea)

qqnormCharacter(centaurea, character = "SF")

## Not run: qqnormAll(centaurea, folderName = "../qqnormPlots")

Data Input and Description

Description

This function imports data and produces a morphodata object from it.

Usage

read.morphodata(file, dec = ".", sep = "\t", ...)

## S3 method for class 'morphodata'

samples(object)

populations(object)

taxa(object)

Arguments

Details

The function expects the following data structure:
(1) the first row contains variable names;
(2) the following rows contains individuals, single individual per row;
(3) the first three columns include unique identifiers for individuals, populations and taxa/groups, respectively. Columns have to be named as “ID”, “Population” and “Taxon”;
(4) starting from the fourth column, any number of quantitative or binary morphological characters may be recorded. Any variable names can be used (avoiding spaces and special characters);

If there are missing values in the data, they must be represented as empty cells or by the text NA, not zero, space or any other character. Example dataset in txt and xlsx formats are stored in the “extdata” directory of the MorphoTools2 package installation directory. To find the path to the package location run system.file("extdata", package = "MorphoTools2").

Value

an object of class morphodata with the following elements:

See Also

characters

Examples

data = read.morphodata(file = system.file("extdata", "centaurea.txt",
    package = "MorphoTools2"), dec = ".", sep = "\t")

## Not run: data = read.morphodata(file = "morphodata.txt", dec = ".", sep = "\t")

## Not run: data = read.morphodata("clipboard")

summary(data)
samples(data)
populations(data)
taxa(data)

Remove Items (Taxa, Populations, Morphological Characters) from Morphodata Object

Description

These functions remove particular taxa, populations, samples or morphological characters from morphodata object. The samples can be deleted by names using sampleName argument, or each sample above the desired threshold missingPercentage will be deleted. Only one parameter can be specified in one run.

Usage

removeTaxon(object, taxonName)

removePopulation(object, populationName)

removeSample(object, sampleName = NULL, missingPercentage = NA)

removeCharacter(object, characterName)

Arguments

Value

an object of class morphodata with the following elements:

Examples

data(centaurea)

centaurea.3tax = removeTaxon(centaurea, "hybr")
centaurea.PsSt = removeTaxon(centaurea, c("ph", "hybr"))

centaurea.short = removePopulation(centaurea, c("LIP", "PREL"))

centaurea.NA_0.1 = removeSample(centaurea, missingPercentage = 0.1)

centaurea.short = removeCharacter(centaurea, "LL")

Shapiro-Wilk Normality Test

Description

Calculates the Shapiro-Wilk normality test of characters for taxa.

Usage

shapiroWilkTest(object, p.value = 0.05)

Arguments

Value

A data.frame, storing results of Shapiro-Wilk normality test.

Examples

data(centaurea)

sW = shapiroWilkTest(centaurea)

## Not run: exportRes(sW, file = "sW_test.txt")

sW = shapiroWilkTest(centaurea, p.value = NA)

## Not run: exportRes(sW, file = "sW_test.txt")

Stepwise Discriminant Analysis

Description

This function perform stepwise discriminant analysis.

Usage

stepdisc.calc(object, FToEnter = 0.15, FToStay = 0.15)

Arguments

Details

The stepdisc.calc function performs a stepwise discriminant analysis to select the “best” subset of the quantitative variables for use in discriminating among the groups (taxa).

Value

None. Used for its side effect.

Examples

data(centaurea)
centaurea = naMeanSubst(centaurea)
centaurea = removePopulation(centaurea, populationName = c("LIP", "PREL"))

stepdisc.calc(centaurea)

Object Summaries

Description

summary methods for classes morphodata, pcadata, pcoadata, nmdsdata, cdadata, and classifdata.

Usage

## S3 method for class 'morphodata'
summary(object, ...)

## S3 method for class 'pcadata'
summary(object, ...)

## S3 method for class 'pcoadata'
summary(object, ...)

## S3 method for class 'nmdsdata'
summary(object, ...)

## S3 method for class 'cdadata'
summary(object, ...)

## S3 method for class 'classifdata'
summary(object, ...)

Arguments

Value

None. Used for its side effect.

Transformation of Character

Description

This function transforms morphological characters by applying another function passed in the argument.

Usage

transformCharacter(object, character, FUN, newName = NULL)

Arguments

Details

Transformation is applied to characters to improve their distribution (to become normally distributed or at least to achieve lesser deviation from normality). The FUN argument takes any function, able to accept as input any value of the character specified by character argument.

Note that, when using a log transformation, a constant should be added to all values to make them all positive before transformation (if there are zero values in the data), because the argument of the logarithm can be only positive numbers. The arcsine transformation is applicable for proportions and percentages (for values ranging from 0 to 1).

Value

an object of class morphodata with the following elements:

Examples

data(centaurea)

# For a right-skewed (positive) distribution can be used:
# Logarithmic transformation
cTransf = transformCharacter(centaurea, character = "SF", FUN = function(x) log(x+1))
cTransf = transformCharacter(centaurea, character = "SF", FUN = function(x) log10(x+1))
# Square root transformation
cTransf = transformCharacter(centaurea, character = "SF", FUN = function(x) sqrt(x))
# Cube root transformation
cTransf = transformCharacter(centaurea, character = "SF", FUN = function(x) x^(1/3))
# Arcsine transformation
cTransf = transformCharacter(centaurea, character = "SF", FUN = function(x) asin(sqrt(x)))

# For a left-skewed (negative) distribution can be used:
# Logarithmic transformation
cTransf = transformCharacter(centaurea, character="SF", FUN=function(x) log((max(x)+1)-x))
cTransf = transformCharacter(centaurea, character="SF", FUN=function(x) log10((max(x)+1)-x))
# Square root transformation
cTransf = transformCharacter(centaurea, character="SF", FUN=function(x) sqrt((max(x)+1)-x))
# Cube root transformation
cTransf = transformCharacter(centaurea, character="SF", FUN=function(x) ((max(x)+1)-x)^(1/3))
# Arcsine transformation
cTransf = transformCharacter(centaurea, character="SF", FUN=function(x) asin(sqrt((max(x))-x)))

Invoke a Data Viewer

Description

Invoke a spreadsheet-style data viewer on a data stored in morphodata class.

Usage

viewMorphodata(object)

Arguments

Value

None. Used for its side effect.

Examples

data(centaurea)

## Not run: viewMorphodata(centaurea)