LMEffectMatrices: Computing the Effect Matrices
In FranceschiniS/LMWiRe: R Routines for Linear Model with Wide Response

Description Usage Arguments Value Examples

Runs a GLM model and decomposes the outcomes into effect matrices for each model terms

1 2	LMEffectMatrices(ResLMModelMatrix, outcomes, SS = TRUE, newSSmethod = TRUE, contrastList = NA)

`ResLMModelMatrix`	A list of 3 from `LMModelMatrix`
`outcomes`	A nxm matrix with n observations and m response variables
`SS`	a logical whether to compute the effect percentage variations
`newSSmethod`	a logical whether to use the new optimized method to compute SS
`contrastList`	a list of contrast for each parameter. The function creates automatically the list by default

A list with the following elements:

formula: A formula object with the expression of the GLM used to predict the outcomes
design: A nxk data frame with the "free encoded" experimental design.
ModelMatrix: A nxK model matrix specifically encoded for the ASCA-GLM method.
outcomes: A nxm matrix with n observations and m response variables
effectMatrices: A list of p effect matrices for each model terms
modelMatrixByEffect: A list of p model matrices by models terms
predictedvalues: A nxm matrix with the predicted values
residuals: A nxm matrix with the residuals
parameters: A pxm matrix with the coefficients of every parameters by response variables
covariateEffectsNamesUnique: A character vector with the p unique name of the model terms
covariateEffectsNames: A character vector with K names of the coefficients

1
2
3

 data('UCH')
 ResLMModelMatrix <- LMModelMatrix(formula=as.formula(UCH$formula),design=UCH$design)
 LMEffectMatrices(ResLMModelMatrix,outcomes=UCH$outcomes)