[R] combining P values using Fisher's method

Jonathan Baron baron at psych.upenn.edu
Thu Aug 16 23:51:13 CEST 2007


On 08/16/07 12:50, Jiong Zhang, PhD wrote:
> Hi All,
> 
> Can somebody tell me how to use R to combine p values using Fisher's method? thanks.

This might get you started.  It is for the sole purpose of combining
two two-tailed p-values for effects in the same direction.  Thus, it
is not very general.  I think it gives a one-tailed result.  Better
check it.

combine <- function(x,y) return(pchisq(-2*log(x/2)-2*log(y/2),4,low=F))

-- 
Jonathan Baron, Professor of Psychology, University of Pennsylvania
Home page: http://www.sas.upenn.edu/~baron



More information about the R-help mailing list