Dear List, I have computed an F-test on my affy chips in limma comparing 3 groups with 20 samples in each group e.g. ctrl, MA, SA. I get the following list with F statistics and p value : e.g. ID MA...Ctrl SA,,,MA SA,,,Ctrl AveExpr F P,Value adj,P,Val 8157727 0,682329 0,281631 0,963959 6,45911 29,06583 1,69E-09 3,21E-05 My question is how can I get hold on the information on which of the contrast/-s is contributing to the significance? As it is now I only know that my list of significant genes are diff exp in any of the contrasts. Others that have performed similar experiments have used anova and a post-hoc test but I have not been able to find how one should perform a post-hoc test after limmas F-test. Many thanks, Christina [[alternative HTML version deleted]]

Usually you would do pair-wise comparisons using contrasts. Or did you have something else in mind? --Naomi At 10:12 AM 8/26/2010, Christina Orsmark-Pietras wrote: >Dear List, > > > >I have computed an F-test on my affy chips in limma comparing 3 groups with >20 samples in each group e.g. ctrl, MA, SA. I get the following list with F >statistics and p value : e.g. > > > > > >ID > >MA...Ctrl > >SA,,,MA > >SA,,,Ctrl > >AveExpr > >F > >P,Value > >adj,P,Val > > >8157727 > >0,682329 > >0,281631 > >0,963959 > >6,45911 > >29,06583 > >1,69E-09 > >3,21E-05 > > > > > > >My question is how can I get hold on the information on which of the >contrast/-s is contributing to the significance? As it is now I only know >that my list of significant genes are diff exp in any of the contrasts. > > > >Others that have performed similar experiments have used anova and a >post-hoc test but I have not been able to find how one should perform a >post-hoc test after limmas F-test. > > > >Many thanks, > >Christina > > > > > [[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 Naomi S. Altman 814-865-3791 (voice) Associate Professor Dept. of Statistics 814-863-7114 (fax) Penn State University 814-865-1348 (Statistics) University Park, PA 16802-2111

Hi Christina, On 8/26/2010 10:12 AM, Christina Orsmark-Pietras wrote: > Dear List, > > > > I have computed an F-test on my affy chips in limma comparing 3 groups with > 20 samples in each group e.g. ctrl, MA, SA. I get the following list with F > statistics and p value : e.g. > In addition to contrasts (as Naomi already mentioned), you could also use decideTests() with the 'nestedF' method. Best, Jim > > > > > ID > > MA...Ctrl > > SA,,,MA > > SA,,,Ctrl > > AveExpr > > F > > P,Value > > adj,P,Val > > > 8157727 > > 0,682329 > > 0,281631 > > 0,963959 > > 6,45911 > > 29,06583 > > 1,69E-09 > > 3,21E-05 > > > > > > > My question is how can I get hold on the information on which of the > contrast/-s is contributing to the significance? As it is now I only know > that my list of significant genes are diff exp in any of the contrasts. > > > > Others that have performed similar experiments have used anova and a > post-hoc test but I have not been able to find how one should perform a > post-hoc test after limmas F-test. > > > > Many thanks, > > Christina > > > > > [[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 -- James W. MacDonald, M.S. Biostatistician Douglas Lab University of Michigan Department of Human Genetics 5912 Buhl 1241 E. Catherine St. Ann Arbor MI 48109-5618 734-615-7826 ********************************************************** Electronic Mail is not secure, may not be read every day, and should not be used for urgent or sensitive issues