contrasts.fit {limma} | R Documentation |
Given an lm.series
fit for a oneway model, compute estimated coefficients and standard errors for a given set of contrasts.
contrasts.fit(fit,contrasts)
fit |
object produced by the function lm.series or equivalent. A list containing components coefficients and stdev.unscaled . |
contrasts |
matrix with columns containing contrasts. May be a vector if there is only one contrast. |
This function accepts input from any of the functions lm.series
, rlm.series
or gls.series
.
The design matrix used for this fit must have orthogonal columns.
The idea is to fit a saturated oneway model using of the above functions, then use contrasts.fit
to obtain coefficients and standard errors for any number of contrasts of the coefficients of the oneway model.
An object of the same type as produced by lm.series
. This is a list components
coefficients |
numeric matrix containing the estimated coefficients for each contrasts for each gene. |
stdev.unscaled |
numeric matrix conformal with coef containing the unscaled standard deviations for the coefficient estimators. |
... |
any other components input in fit |
Gordon Smyth
An overview of linear model functions in limma is given by 5.LinearModels.
# Simulate gene expression data, # 6 microarrays and 100 genes with one gene differentially expressed in first 3 arrays M <- matrix(rnorm(100*6,sd=0.3),100,6) M[1,1:3] <- M[1,1:3] + 2 # Design matrix corresponds to oneway layout, columns are orthogonal design <- cbind(First3Arrays=c(1,1,1,0,0,0),Last3Arrays=c(0,0,0,1,1,1)) fit <- lm.series(M,design=design) # Would like to consider original two estimates plus difference between first 3 and last 3 arrays contrast.matrix <- cbind(First3=c(1,0),Last3=c(0,1),"Last3-First3"=c(-1,1)) fit2 <- contrasts.fit(fit,contrasts=contrast.matrix) eb <- ebayes(fit2) # Large values of eb$t indicate differential expression clas <- classifyTestsF(eb$t,design=design,contrasts=contrast.matrix,df=fit2$df+eb$df)