decideTests {limma} | R Documentation |
Classify a series of related t-statistics as up, down or not significant.
decideTests(object,method="separate",adjust.method="fdr",p.value=0.05)
object |
MArrayLM object output from eBayes from which the t-statistics may be extracted. |
method |
character string specify how probes and contrasts are to be combined in the multiple testing strategy. Choices are "separate" , "global" , "heirarchical" , "nestedF" or any partial string. |
adjust.method |
character string specifying p-value adjustment method. See p.adjust for possible values. |
p.value |
numeric value between 0 and 1 giving the desired size of the test |
These functions implement multiple testing procedures for determining whether each statistic in a matrix of t-statistics should be considered significantly different from zero.
Rows of tstat
correspond to genes and columns to coefficients or contrasts.
The setting method="separate"
is equivalent to using topTable
separately for each coefficient in the linear model fit, and will give the same lists of probes if adjust.method
is the same.
Note that the defaults for adjust.method
are different for decideTests
and topTable
.
method="global"
will treat the entire matrix of t-statistics as a single vector of unrelated tests.
method="heirarchical"
adjusts down genes and then across contrasts.
method="nestedF"
adjusts down genes and then uses classifyTestsF
to classify contrasts as significant or not for the selected genes.
An object of class TestResults
.
This is essentially a numeric matrix with elements -1
, 0
or 1
depending on whether each t-statistic is classified as significantly negative, not significant or significantly positive respectively.
Gordon Smyth
An overview of multiple testing functions is given in 08.Tests.