[BioC] Dual color chip analysis : duplicateCorrelation

[James W. MacDonald]

Hi Guillaume,

Please don't resend identical questions to the list with different 
subject lines. For that matter, please don't resend identical questions 
with the same subject line either.

I understand that this question is interesting to you, but you have to 
understand that the purpose of this list is to answer technical 
questions about how to use BioC packages. Your question is statistical 
in nature, and not many are interested in teaching statistics via email. 
This is especially true given the amount of information available on the 
subject on the internet.

If you read the limma User's Guide closely, you will see that you are 
fitting two different models. One is a standard ANOVA model, and the 
other is a mixed model. Simplistically, the difference between the two 
is that ANOVA assumes that each group you are modeling has similar 
intra-group variance, and the only difference is the mean expression. A 
mixed model is a more general model that accounts for any differences in 
intra-group variances.

So you should not be particularly surprised that there are different 
results, since you are fitting different models. The question isn't 
which one you should trust. The real question is what assumptions are 
you willing to make about your data and why.

Best,

Jim



On 2/18/2011 8:15 AM, Guillaume Meurice wrote:
> Dear all,
>
>
> I was wondering why there is so many difference between the two following approaches  to handle the replication for my experiments - therefore, I don't which one to trust.
>
>
> briefly, Here is my target :
> Cy3	Cy5
> wt1	mu1
> mu1	wt1
> wt2	mu2
> mu2	wt2
> wt3	mu3
> mu3	wt3
>
>
> to get the gene differentially expressed between Mutant and WT, I have stricly followed the two solutions given in the page 37 of limma userguide (3rd apriol 2010):
> - the first one (page 37) is using duplicateCorrelation
> - the second one clearly explicit the design matrix and the contrast matrix (page 38) as follow
>
> design = cbind(
> 		R1_MuvsWT = c(-1,1,0,0,0,0),
> 		R2_MuvsWT = c(0,0,-1,1,0,0),
> 		R3_MuvsWT = c(0,0,0,0,-1,1)
> )
> fit = lmFit(MAn,design)
>
> cont.matrix = makeContrasts (
> 		MuvsWT = (R1_MuvsWT + R2_MUvsWT+R3_MUvsWT)/3,
> 		levels = design
> )
>
>
> using these two approaches give quantitatively different results.
>
>
> Which one should I trust ?
>
> Thanks by advance for any pieces of advice and / or any help
>
> Cheers
>
> --
> G.M
> --
> Guillaume Meurice - PhD
> Bioinformaticien
>
> Unité de Génomique Fonctionnelle
>
> PR2 - Bureau 323.2
> Poste : 3509
>
> Institut Gustave Roussy - PR2
> 114 rue Edouard Vaillant - 94805 VILLEJUIF Cedex
> tel	: +33 (0)1 42 11 42 11 (poste 3509)
> fax	: +33 (0)1 42 11 62 67
>
>
> 	[[alternative HTML version deleted]]
>
>
>
>
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at r-project.org
> 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