[BioC] decideTests

Gordon Smyth smyth at wehi.edu.au
Thu Nov 4 02:44:17 CET 2004


>Wed Nov 3 17:37:22 CET 2004
>Hi All
>
>Trying to use decideTests (for the first time)
>the following command works fine with classify tests
>
>CLASTEST <- classifyTestsP(EB$t, df=Inf, p.value=0.2, method="fdr")
>
>but the same objects either EB$t or FIT(MAarryLM) don't appear to work
>at all
>
>DT <- decideTests(EB$t, p.value=0.2, method="separate", adjust.method="fdr")

You need

DT <- decideTests(EB, p.value=0.2, method="separate", adjust.method="fdr")

>returns:
>Error in decideTests(nwaKarinaKoopEB$t, p.value = 0.2, method =
>"separate",  :
>         Need MArrayLM object
>
>DT <- decideTests(FIT, p.value=0.2, method="separate", adjust.method="fdr")
>
>returns:
>Error in array(x, c(length(x), 1), if (!is.null(names(x))) list(names(x),  :
>         attempt to set an attribute on NULL

This is because FIT doesn't contain the output from eBayes(), i.e., doesn't 
contain t-statistics.

>In both classifyTests and decideTest the object being specified is
>described as:
>
>Arguments
>|object|        numeric matrix of t-statistics or an |MArrayLM| object from
>which the t-statistics may be extracted.

Sorry, the doc is wrong in that support for a "matrix of t-statistics" 
hasn't been implemented.

Gordon

>any ideas ?
>
>using
>R 2.0
>limma 1.8.6
>
>Thx
>
>--
>--------------------------------
>Jason Skelton
>Pathogen Microarrays
>Wellcome Trust Sanger Institute
>Hinxton
>Cambridge
>CB10 1SA



More information about the Bioconductor mailing list