pca: Perform Principal Component Analysis

Description Usage Arguments Details Value Author(s) References See Also

View source: R/pca.R

Description

This function is used to perform Principal Component Analysis (PCA).

Usage

1
pca(X, pc = 2, scale = "UV", center = T, method = "nipals")

Arguments

X

Numeric input matrix with each row representing an observation and each column a metabolic feature.

pc

Desired number of principal components.

scale

Desired scaling method: None, UV (unit variance) or Pareto (Pareto scaling).

center

Logical indicating if data should be mean centered.

method

Algorithm for computing PCA. NIPALS is standard and usually fine. It can handle small amounts of missing/NA values.

Details

Other methods include: 'svd', 'rnipals', 'bpca', 'ppca', 'svdImpute', 'robustPca', 'nlpca', 'llsImpute', 'llsImputeAll'. If these methods are specified, the pca function from the pcaMethods package is used to fit PCA model (see References).

Value

This function returns a PCA_MetaboMate S4 object.

Author(s)

Torben Kimhofer tkimhofer@gmail.com

References

Geladi, P and Kowalski, B.R. (1986), Partial least squares and regression: a tutorial. Analytica Chimica Acta, 185, 1-17.

See Also

PCA_MetaboMate pca plotscores plotload opls


kimsche/MetaboMate documentation built on Aug. 8, 2020, 1:14 a.m.