plsreg2: PLS-R2: Partial Least Squares Regression 2

View source: R/plsreg2.R

plsreg2R Documentation

PLS-R2: Partial Least Squares Regression 2

Description

The function plsreg2 performs partial least squares regression for the multivariate case (i.e. more than one response variable)

Usage

  plsreg2(predictors, responses, comps = 2, crosval = TRUE)

Arguments

predictors

A numeric matrix or data frame containing the predictor variables.

responses

A numeric matrix or data frame containing the response variables.

comps

The number of extracted PLS components (2 by default)

crosval

Logical indicating whether cross-validation should be performed (TRUE by default). No cross-validation is done if there is missing data or if there are less than 10 observations.

Details

The minimum number of PLS components comps to be extracted is 2.

The data is scaled to standardized values (mean=0, variance=1).

The argument crosval gives the option to perform cross-validation. This parameter takes into account how comps is specified. When comps=NULL, the number of components is obtained by cross-validation. When a number of components is specified, cross-validation results are calculated for each component.

Value

An object of class "plsreg2", basically a list with the following elements:

x.scores

components of the predictor variables (also known as T-components)

x.loads

loadings of the predictor variables

y.scores

components of the response variables (also known as U-components)

y.loads

loadings of the response variables

cor.xt

correlations between X and T

cor.yt

correlations between Y and T

cor.xu

correlations between X and U

cor.yu

correlations between Y and U

cor.tu

correlations between T and U

raw.wgs

weights to calculate the PLS scores with the deflated matrices of predictor variables

mod.wgs

modified weights to calculate the PLS scores with the matrix of predictor variables

std.coefs

Vector of standardized regression coefficients (used with scaled data)

reg.coefs

Vector of regression coefficients (used with the original data)

y.pred

Vector of predicted values

resid

Vector of residuals

expvar

table with R-squared coefficients

VIP

Variable Importance for Projection

Q2

table of Q2 indexes (i.e. leave-one-out cross validation)

Q2cum

table of cummulated Q2 indexes

Author(s)

Gaston Sanchez

References

Geladi, P., and Kowlaski, B. (1986) Partial Least Squares Regression: A Tutorial. Analytica Chimica Acta, 185, pp. 1-17.

Hoskuldsson, A. (1988) PLS Regression Methods. Journal of Chemometrics, 2, pp. 211-228.

Tenenhaus, M. (1998) La Regression PLS. Theorie et Pratique. Editions TECHNIP, Paris.

See Also

plot.plsreg2, plsreg1.

Examples

## Not run: 
 ## example of PLSR2 with the vehicles dataset
 data(vehicles)

 # apply plsreg2 extracting 2 components (no cross-validation)
 pls2_one = plsreg2(vehicles[,1:12], vehicles[,13:16], comps=2, crosval=FALSE)

 # apply plsreg2 with selection of components by cross-validation
 pls2_two = plsreg2(vehicles[,1:12], vehicles[,13:16], comps=NULL, crosval=TRUE)

 # apply plsreg2 extracting 5 components with cross-validation
 pls2_three = plsreg2(vehicles[,1:12], vehicles[,13:16], comps=5, crosval=TRUE)

 # plot variables
 plot(pls2_one)
 
## End(Not run)

plsdepot documentation built on April 1, 2023, 12:04 a.m.