[BioC] lmFit function

[Jenny Drnevich]

Hi Priscila,

The robustspline method for normalization has 
nothing to do with the lmFit(method="robust"). 
lmFit can either fit the model using a least 
squares regression or a robust regression, which 
down-weights replicates that are different from 
the other replicates. Whether or not to use 
lmFit(method="robust") doesn't depend on which 
normalization method you use, but rather (IMO) 
how many replicates you have. If you have a 
relatively large number of replicates, say 6 or 
more, then the robust fitting of the model may 
help to remove true outliers from affecting the 
data. However, if you only have 3 replicates, as 
is usual for microarray experiments, using the 
robust estimation may remove real variation in 
your samples and lead to more false-positives.

That's my take on the situation...
Jenny

At 10:49 AM 1/8/2009, Priscila Grynberg wrote:
>Content-Type: text/plain
>Content-Disposition: inline
>Content-length: 1308
>
>Hi BioCs,
>I have a doubt about this function.
>
>I'm working with a two-channel dye-swap microarray experiments. After
>testing all normalization methods, I conclude that the robustspline method
>was the best for my data. After normalizing, I did the statistical analysis
>using the lmFit and eBayes functions.
>
>My commands were:
>
>fit <- lmFit(MA, design, ndups=2, spacing=12, cor=corfit$consensus)
>
>fit2 <- eBayes(fit)
>
>Everything worked just fine. However, I read the lmFit help and a doubt came
>up:
>
>lmFit(object,design=NULL,ndups=1,spacing=1,block=NULL,correlation,weights=NULL,
>method="ls",...)
>
>method: character string, "ls" for least squares or "robust" for robust
>regression
>
>Then, I repeat the same commands, but changing the parameter "method", since
>I used the robustspline method for normalization. I got different top 100
>genes most differentially expressed. And now I really confused. I don't know
>what to do with this "method" parameter.
>
>I hope someone can explain to me!
>
>Thanks,
>
>Priscila
>
>
>
>
>--
>Priscila Grynberg, B.Sc., M.Sc.
>Doutoranda em Bioinformática (Bioinformatics D.Sc student)
>Laboratório de Genética Bioquímica
>Universidade Federal de Minas Gerais
>Tel: +55 31 3409-2628
>CV: http://lattes.cnpq.br/8808643075395963
>
>         [[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

Jenny Drnevich, Ph.D.

Functional Genomics Bioinformatics Specialist
W.M. Keck Center for Comparative and Functional Genomics
Roy J. Carver Biotechnology Center
University of Illinois, Urbana-Champaign

330 ERML
1201 W. Gregory Dr.
Urbana, IL 61801
USA

ph: 217-244-7355
fax: 217-265-5066
e-mail: drnevich at illinois.edu