run.pca: Principal Component Analysis function

In jmcole003/pcanalysis: Principal Components Analysis Package

Description

This function performs a principal component analysis on a numerical data matrix.

Usage

run.pca(x, center = TRUE, scale = FALSE, svd = TRUE)

Arguments

x	input data matrix or data frame (numerical)
center	zero center the data (logical value, default is TRUE)
scale	scale the data to unit variance before analysis (logical value, default is FALSE)
svd	indicate whether to perform single value decomposition (logical value, default is TRUE), otherwise perform eigen decomposition

Value

run.pca returns a list with the following elements:

• Data - a preview of the input data matrix

• k - the number of observations in the dataset

• PCs - the matrix of loadings containing the principal components as columns (eg, eigenvectors)

• sdev - standard deviations of the principal components (uses singular values of the matrix if using singular value decomposition, but takes the square root of the eigenvalues of the correlation matrix if using spectral decomposition)

Examples

data.pca <- run.pca(data, center = TRUE, scale = TRUE, svd = TRUE)

jmcole003/pcanalysis documentation built on Dec. 21, 2021, 1:12 a.m.