leverage {lmdme} | R Documentation |
leverage
test of lmdme objectsThis function calculates the leverage test for each individual using the Principal Component Analysis (comps function) on the coefficients of the given decomposed model term.
object |
lmdme class object. |
comps |
a numeric vector indicating the PCA component indexes to keep. Default the first two components (1:2). |
term |
a character specifying the model term. |
level |
the quantile level. Default value 0.95 |
data.frame with the following fields
leverage |
numeric for the corresponding row leverage |
over |
logical indicating if the leverage > quantile(leverage,level) for the given decomposed term |
Cristobal Fresno and Elmer A Fernandez
Tarazona S, Prado-Lopez S, Dopazo J, Ferrer A, Conesa A, Variable Selection for Multifactorial Genomic Data, Chemometrics and Intelligent Laboratory Systems, 110:113-122 (2012)
{ data(stemHypoxia) ##Just to make a balanced dataset in the Fisher sense (2 samples per ## time*oxygen levels) design<-design[design$time %in% c(0.5, 1, 5) & design$oxygen %in% c(1,5,21),] design$time<-as.factor(design$time) design$oxygen<-as.factor(design$oxygen) rownames(M)<-M[, 1] ##Keeping appropriate samples only M<-M[, colnames(M) %in% design$samplename] ##ANOVA decomposition fit<-lmdme(model=~time+oxygen+time:oxygen, data=M, design=design) ##Leverages for the first two Principal Components and q95 (default value). ##Leverages for the first three Principal Components and q99. leverages2PCDefault<-leverage(fit, term="time:oxygen") leverages3PCq99<-leverage(fit, comps=1:3, term="time:oxygen", level=0.99) }