[R] p-values from multiple testing

[Jie]

Dear All,

I performed thousands of testings and obtained p-values.
And then I did two-sided uniform KS test of the p-values, the result
claimed it is uniform.
So does it mean that my model are wrong? Because I expect more small
p-values near 0.
This is a preliminary step before correcting the multiplicity.
Attached is hist of p-values (does this list allow attachment?). The ks test:

One-sample Kolmogorov-Smirnov test

D = 0.0493, p-value = 1.388e-06

alternative hypothesis: two-sided

Thank you for your attention.

Best wishes,
Jie
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Untitled.png
Type: image/png
Size: 23284 bytes
Desc: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20130723/ac5b93f8/attachment.png>