2-way Anova analysis
4
0
Entering edit mode
Sharon Anbu ▴ 480
@sharon-anbu-1524
Last seen 9.7 years ago
An embedded and charset-unspecified text was scrubbed... Name: not available Url: https://stat.ethz.ch/pipermail/bioconductor/attachments/20060105/ 32ffd638/attachment.pl
• 449 views
ADD COMMENT •
0
Entering edit mode
Sharon Anbu ▴ 480
@sharon-anbu-1524
Last seen 9.7 years ago
An embedded and charset-unspecified text was scrubbed... Name: not available Url: https://stat.ethz.ch/pipermail/bioconductor/attachments/20060105/ c44bedfc/attachment.pl
ADD COMMENT •
0
Entering edit mode
Sharon wrote: > Hi All, > > I am trying to analyze affy data for strain, treatment and their interaction > effects (RMA normalized, log2 expression values). The design looks like > > strain A --> treatment 1 strain B --> treatment 1 > treatment 2 treatment 2 > > so, I used anova(aov(expra ~ strain + treatment + strain*treatment, m)), > where m <- data.frame(strain, treatment, expr) > > I have got the corresponding pvalues for strain, treatment & interaction > effects( this for all the probsets). Now, I would like to separate the > number of significant probesets for strain A and strain B from strain effect > (I would like to do the same for treatment effect). How can I do this? Any > help is very much appreciated. I am not sure exactly what you are asking for here, but you are probably better off using the limma package. After fitting the model you can then use e.g., decideTests() and vennDiagram() to get the number of probesets significant in contrasts of interest. There is an excellent User's Guide that accompanies this package that will answer about 90% of the questions you may have. HTH, Jim > > Thanks in Advance. > Regards, > Sharon > > [[alternative HTML version deleted]] > > _______________________________________________ > Bioconductor mailing list > Bioconductor at stat.math.ethz.ch > https://stat.ethz.ch/mailman/listinfo/bioconductor -- James W. MacDonald University of Michigan Affymetrix and cDNA Microarray Core 1500 E Medical Center Drive Ann Arbor MI 48109 734-647-5623 ********************************************************** Electronic Mail is not secure, may not be read every day, and should not be used for urgent or sensitive issues.
ADD REPLY •
0
Entering edit mode
Sharon Anbu ▴ 480
@sharon-anbu-1524
Last seen 9.7 years ago
An embedded and charset-unspecified text was scrubbed... Name: not available Url: https://stat.ethz.ch/pipermail/bioconductor/attachments/20060106/ 4747e4e9/attachment.pl
ADD COMMENT •
0
Entering edit mode
Sharon wrote: > Hi Donglei & James > > > Thanks for your reply. I am sorry for not making myself clear. I already > have this matrix that contains Probeset p-value (strain effect) p-value > (treatment effect) p-value (interaction). As you suggested, I can use > pvalue cut-off to select probesets for strain effect. From the selected list > (for strain effect), I would like to choose probsets that are significant > for Strain A and then for Strain B. In the same way, I would like to select > probesets for Treatment A and Treatment B. I think you might be misunderstanding what significance means in this context. If there is a significant strain effect for a particular probeset (assuming there isn't a significant interaction term for that probeset), this simply means that there is a significant _difference_ between the two strains for that probeset. Therefore you cannot attribute significance to either strain since it is the difference in expression that is significant. HTH, Jim > > I hope, this explains my problem. > Thanks again, > Sharon -- James W. MacDonald University of Michigan Affymetrix and cDNA Microarray Core 1500 E Medical Center Drive Ann Arbor MI 48109 734-647-5623 ********************************************************** Electronic Mail is not secure, may not be read every day, and should not be used for urgent or sensitive issues.
ADD REPLY •
0
Entering edit mode
Naomi Altman ★ 6.0k
@naomi-altman-380
Last seen 3.1 years ago
United States
Dear Sharon, I think that what you mean is that you want to consider the treatment effect within strain. To do this, you simply create 2 contrasts - one for each strain. The coefficients for the other strain will be 0. --Naomi At 04:08 AM 1/6/2006, Sharon wrote: >Hi Donglei & James > > >Thanks for your reply. I am sorry for not making myself clear. I already >have this matrix that contains Probeset p-value (strain effect) p-value >(treatment effect) p-value (interaction). As you suggested, I can use >pvalue cut-off to select probesets for strain effect. From the selected list >(for strain effect), I would like to choose probsets that are significant >for Strain A and then for Strain B. In the same way, I would like to select >probesets for Treatment A and Treatment B. > >I hope, this explains my problem. >Thanks again, >Sharon > > >On 1/5/06, donghu at itsa.ucsf.edu <donghu at="" itsa.ucsf.edu=""> wrote: > > > > Hi, > > > > You can make a matrix which has 4 columns: > > > > Probeset p-value (strain effect) p-value (treatment effect) p-value > > (interaction) > > > > Then you can select probe sets based on these p-values. > > > > Hope this helps. > > > > Donglei Hu > > > > On Thu, 5 Jan 2006 15:26:15 +0100 Sharon wrote: > > > > > Hi All, > > > > > > I am trying to analyze affy data for strain, treatment and their > > > interaction > > > effects (RMA normalized, log2 expression values). The design looks like > > > > > > strain A --> treatment 1 strain B --> treatment 1 > > > treatment 2 treatment 2 > > > > > > so, I used anova(aov(expra ~ strain + treatment + strain*treatment, m)), > > > where m <- data.frame(strain, treatment, expr) > > > > > > I have got the corresponding pvalues for strain, treatment & interaction > > > effects( this for all the probsets). Now, I would like to separate the > > > number of significant probesets for strain A and strain B from strain > > > effect > > > (I would like to do the same for treatment effect). How can I do > > > this? Any > > > help is very much appreciated. > > > > > > Thanks in Advance. > > > Regards, > > > Sharon > > > > > > [[alternative HTML version deleted]] > > > > > > _______________________________________________ > > > Bioconductor mailing list > > > Bioconductor at stat.math.ethz.ch > > > https://stat.ethz.ch/mailman/listinfo/bioconductor > > > > > > > > > > > [[alternative HTML version deleted]] > >_______________________________________________ >Bioconductor mailing list >Bioconductor at stat.math.ethz.ch >https://stat.ethz.ch/mailman/listinfo/bioconductor 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
ADD COMMENT •
0
Entering edit mode
Sharon Anbu ▴ 480
@sharon-anbu-1524
Last seen 9.7 years ago
An embedded and charset-unspecified text was scrubbed... Name: not available Url: https://stat.ethz.ch/pipermail/bioconductor/attachments/20060109/ a9dec95a/attachment.pl
ADD COMMENT •

Login before adding your answer.

Similar Posts
Loading Similar Posts
Traffic: 573 users visited in the last hour
Content Search
Users
Tags
Badges
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6