CODEWITHSUNDEEP
rstatisticsstatistical-test
user11538509
user11538509

Reputation:

Exact Cochran's Q test in R

I need to run a Cochran's test with small sample sizes. I read that "If your sample size is inadequate, the asymptotic p-value may not be accurate, but you can run an "exact" version of Cochran's Q test that will generate a more accurate exact p-value" (here).

The "nonpar" package for R offers different tests and in many cases there is the option exact= TRUE which can be used if one wants to avoid approximation. However, there is no such option for the cochrans.q() function. How can I know whether an approximation or exact approach is used in cochrans.q()?

I am unsure whether to post the question here or on Cross Validated. So please migrate the question if it should go to SO.

Upvotes: 2

Views: 579

Answers (1)

Julius Vainora
Julius Vainora

Reputation: 48211

It uses the asymptotic approximation. It can be seen in the source code of (just type cochrans.q) as it contains

p = 1 - pchisq(Q, df)

Upvotes: 1

Related Questions