An embedded and charset-unspecified text was scrubbed... Name: not available Url: https://stat.ethz.ch/pipermail/bioconductor/attachments/20070924/ 428be3dd/attachment.pl

Dear Ingrid, These warnigns mean that there are 9 genes in which a few data points are substantially influential to the regression model. These could be outliers and therefore it is recommended to look in more detail into these genes and remove from the analysis if necessary. You can find these genes under the slot influ.info. of the T.fit object. Best regards Ana Conesa Bioinformatics Department Centro de Investigaciones Principe Felipe Avda. Autopista Saler 16 46013 Valencia Spain http://bioinfo.cipf.es Ingrid H. G. ?stensen wrote: > Hi > > I am trying to learn the maSigPro package but I get a warning: > >> tstep <- T.fit(fit, design = fit$dis, step.method = "backward", min.obs = design$min.obs, alfa = fit$Q, nvar.correction = FALSE) > [1] "Warning: 9 genes with influential data at slot influ.info. Model validation for these genes is recommended" > > I get a similar warning when I use the example data set. > > What does it mean? > > >> sessionInfo() > R version 2.5.1 (2007-06-27) > i386-pc-mingw32 > > locale: > LC_COLLATE=English_United Kingdom.1252;LC_CTYPE=English_United Kingdom.1252;LC_MONETARY=English_United Kingdom.1252;LC_NUMERIC=C;LC_TIME=English_United Kingdom.1252 > > attached base packages: > [1] "tools" "stats" "graphics" "grDevices" "utils" "datasets" "methods" "base" > > other attached packages: > maSigPro Biobase xtable impute limma > "2.0.1" "1.14.1" "1.5-1" "1.0-5" "2.10.5" > > > Regards, > Ingrid > > [[alternative HTML version deleted]] > > _______________________________________________ > Bioconductor mailing list > Bioconductor at stat.math.ethz.ch > https://stat.ethz.ch/mailman/listinfo/bioconductor > Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor