PCA: Principal Components Analysis

In Rkabacoff/qacr: Functions to Facilitate Data Science Projects

Description

PCA performs a principal components analysis

Usage

PCA(data, nfactors = NULL, rotate = "none", digits = 2, ...)

Arguments

data	a data frame or correlation matrix.
nfactors	nuber of factors to extract.
rotate	factor rotation to perform.
digits	number of digits to retain.
...	parameters passed to the psych::principal function.

Details

The PCA function is a wrapper for the psych::principal function. Component rotations include none, varimax, and promax.

Value

returns a list with 5 components:

call	the call
loadings	structure matrix
variance	variance accounted for
phi	component intercorrelations for oblique rotations
scores	component scores if factors are extracted from a data frame

See Also

FA, plot.factorAnalysis, score, and scree_plot.

Examples

fit.pca <- PCA(Harman74.cor$cov, nfactors=4, rotate="varimax")
plot(fit.pca)
plot(fit.pca, type="bar")

Rkabacoff/qacr documentation built on March 20, 2021, 3:03 p.m.