**0**wrote:

Hi,

our group has been using the function *DESeq** *of the library* DESeq2* to perform differential expression analysis. We notice than some features get a p-value much smaller than the machine epsilon. There are two points that we find difficult to understand.

1. How are these functions generating the p-values, especially those that are smaller than the epsilon of the machine?

2. How meaningful is a comparison of p-values that are negligibly small, say 10^(-250) and 10^(-251)?

We would deeply appreciate any help for the understanding of these questions.

O.F.

**24k**• written 8 months ago by oscarf •

**0**

Here's a link to a similar thread about edgeR:

p -values smaller than machine epsilon in edgeR

24k