That's right. The avedups() function in fact assumes the same number of replicates (as for the duplicateCorrelation function). The situation is clouded slightly by missing values,so I recommend that Weiyin pre-process to avoid them. Cheers Gordon At 12:55 PM 13/12/2006, Naomi Altman wrote: >You have to be a bit careful here. Averaging works if all the genes >have the same number of replicates. If not, then averaging will >violate the variance assumptions, although you might be able to >mitigate this by using spot weights. On spotted arrays, one usually >does have the same number of replicates, but on Agilent arrays, it >is up to the array designer. > >--Naomi > >At 04:58 PM 12/12/2006, Gordon K Smyth wrote: >>On Wed, December 13, 2006 5:16 am, Weiyin Zhou wrote: >> > Dr. Smyth and limma users, >> > >> > If I want to do separate channel analysis of two-color Agilent data >> > file, how can I deal with replicated spots within array? >> > >> > According to limma User's Guide, Chapter 9, for doing separate channel >> > analysis of two-color data, the correlation to be estimated is that >> > between the two channels for the same spot rather than between >> > replicated spots. So how can I get one value for the replicated spots >> > within array? In ratio base, it gets one p value for the replicated >> > spots by use function duplicateCorrelation and ndups=2. >> > >> > I am thinking maybe I should do average of replicated spots within array >> > first, then do intraspotCorrelation to get estimate the correlation. >> >>That's what I would do. >> >> > But I don't know what kind of function available for doing it? >> >>?avedups >> >>Best wishes >>Gordon >> >> > >> > >> > >> > Could you help me? >> > Thanks in advance, >> > >> > Regards, >> > >> > Weiyin Zhou >> > Statistics and Data Analyst >> > ExonHit Therapeutics, Inc. >> > 217 Perry Parkway, Building # 5 >> > Gaithersburg, MD 20877 >> > >> > email: Weiyin.zhou at exonhit-usa.com <mailto:weiyin.zhou at="" exonhit-usa.com=""> >> > phone: 240.404.0184 >> > fax: 240.683.7060 >> >>_______________________________________________ >>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 >