Dear List, I am working on a data set generated using Illumina's methylation 450K array. The goal is to identify regions that are differentially methylated between cases and controls. It seems that people are using beta value difference and Wilcoxon Rank Sum test for this kind of analysis. My question is what will be a good cutoff to use for the beta value difference. I have seen people using 0.2, but not sure whether that is just generally accepted or there is other approaches that are more statistically sounding. How to justify if a lower beta value difference, e.g. 0.1, is to be used? Any suggestions will be highly appreciated. Nancy Chen Biomedical Informatics Specialist City of Hope --------------------------------------------------------------------- *SECURITY/CONFIDENTIALITY WARNING: This message and any attachments are intended solely for the individual or entity to which they are addressed. This communication may contain information that is privileged, confidential, or exempt from disclosure under applicable law (e.g., personal health information, research data, financial information). Because this e-mail has been sent without encryption, individuals other than the intended recipient may be able to view the information, forward it to others or tamper with the information without the knowledge or consent of the sender. If you are not the intended recipient, or the employee or person responsible for delivering the message to the intended recipient, any dissemination, distribution or copying of the communication is strictly prohibited. If you received the communication in error, please notify the sender immediately by replying to this message and deleting the message and any accompanying files from your system. If, due to the security risks, you do not wish to receive further communications via e-mail, please reply to this message and inform the sender that you do not wish to receive further e-mail from the sender. --------------------------------------------------------------------- [[alternative HTML version deleted]]

Cutoffs for beta values depend upon the mean. You might want to use m-values, i.e. log2( beta / (1-beta)), if a consistent cutoff is important to you. However, be aware that you will then be looking at differences on a scale of fold-changes, and should consider transforming back to proportions (beta values) to interpret them. See http://www.biomedcentral.com/1471-2105/11/587 for more on the subject. On Wed, Dec 14, 2011 at 10:13 AM, Chen, Zhuo <zhuchen@coh.org> wrote: > Dear List, > > I am working on a data set generated using Illumina's methylation 450K > array. The goal is to identify regions that are differentially methylated > between cases and controls. It seems that people are using beta value > difference and Wilcoxon Rank Sum test for this kind of analysis. My > question is what will be a good cutoff to use for the beta value > difference. I have seen people using 0.2, but not sure whether that is just > generally accepted or there is other approaches that are more statistically > sounding. How to justify if a lower beta value difference, e.g. 0.1, is to > be used? > > Any suggestions will be highly appreciated. > > Nancy Chen > Biomedical Informatics Specialist > City of Hope > > > > --------------------------------------------------------------------- > *SECURITY/CONFIDENTIALITY WARNING: > This message and any attachments are intended solely for the individual or > entity to which they are addressed. This communication may contain > information that is privileged, confidential, or exempt from disclosure > under applicable law (e.g., personal health information, research data, > financial information). Because this e-mail has been sent without > encryption, individuals other than the intended recipient may be able to > view the information, forward it to others or tamper with the information > without the knowledge or consent of the sender. If you are not the intended > recipient, or the employee or person responsible for delivering the message > to the intended recipient, any dissemination, distribution or copying of > the communication is strictly prohibited. If you received the communication > in error, please notify the sender immediately by replying to this message > and deleting the message and any accompanying files from your system. If, > due to the security risks, you do not wi! > sh to receive further communications via e-mail, please reply to this > message and inform the sender that you do not wish to receive further > e-mail from the sender. > > --------------------------------------------------------------------- > > > [[alternative HTML version deleted]] > > _______________________________________________ > Bioconductor mailing list > Bioconductor@r-project.org > https://stat.ethz.ch/mailman/listinfo/bioconductor > Search the archives: > http://news.gmane.org/gmane.science.biology.informatics.conductor > -- If people do not believe that mathematics is simple, it is only because they do not realize how complicated life is. John von Neumann<http: www-groups.dcs.st-="" and.ac.uk="" ~history="" biographies="" von_neumann.html=""> [[alternative HTML version deleted]]