[BioC] how to combine p values?

[Moshe Olshansky]

Hi Reema,

there are several ways to do so (you can search the Internet). I am not sure whether there exists a really good one.
One possibility is as below:
let P1 and P2 be the p-values from dataset 1 and dataset 2. Under the null hypothesis both p-values are distributed uniformly in [0,1]. If we assume independence then the probability that their product is less than x equals x - x*log(x) (where log is the natural - base e - logarithm). So your combined p-value is P1*P2 - P1*P2*log(P1*P2).

Best regards,
Moshe. 

--- On Thu, 9/12/10, Reema Singh <reema28sep at gmail.com> wrote:

> From: Reema Singh <reema28sep at gmail.com>
> Subject: [BioC] how to combine p values?
> To: bioconductor at r-project.org
> Received: Thursday, 9 December, 2010, 8:50 PM
> Hi All
> 
> I want to combine the two datasets using p-values.
> Can anybody tell me how to combine p values from two
> different datasets
> using R?
> 
> It would be a great help
> 
> Waiting for reply....
> 
> REGARDS~
> Reema Singh
> 
>     [[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
>