CODEWITHSUNDEEP
rbioconductorp-valuegenome
user2120870
user2120870

Reputation: 869

p.adjust with n < than number of tests

I would like to apply the p.adjust function in R where n is < number of p-values. The real number of independent tests is lower than the number of p-values as it cames from genomic data with Linkage Desequilibrium Desequilibrium (effective number of independent tests, Meff).

However, the p.adjust function do not allows it: number of comparisons, must be at least length(p).

Someone knows how to change this default in function or other generic function to accomplish similar work? Thank you!

Followed Steps:

1 - 3242 tested markers = 3242 p-values

2 - Inferred Meff is: 1096 (http://simplem.sourceforge.net/ procedure)

Now I need to estimate the corrected treshould or corrected p-values based on Meff.

I am not sure which multiple test correction strategy fits better or how to apply it in my data.

Upvotes: 1

Views: 1133

Answers (2)

jakz
jakz

Reputation: 43

When using a smaller n in this way you may end up with p-values that are smaller than their unadjusted counterpart. To avoid this I suggest you can add an additional check to force the new p-values to be minimum the unadjusted p, just before the return of p0:

p0 <- ifelse(p0 < p, p, p0)

Upvotes: 1

IRTFM
IRTFM

Reputation: 263332

The code:

  p.adjust # typed at command line prints out the code
  # copy the body of the function

... is really very simple and all R. Just redefine a function that comments out that stopifnot() line:

my.p.adj <- function (p, method = p.adjust.methods, n = length(p)) 
 # paste the body and edit this:
....
p <- p[nna]
lp <- length(p)
# stopifnot(n >= lp)
if (n <= 1) 
....  # hit enter

Upvotes: 6

Related Questions