1
$\begingroup$

I am working on estimating parameters for a behavioural experiment where the likelihood of my data is modelled as a multinomial with the parameters summing to 1, and I have a weakly informative Dirichlet prior. I have done the usual posterior predictive checks and the multinomial-Dirichlet model seems to work much better than a Gaussian model with log-transformed data.

I am unsure what a good test statistic for hypothesis testing (comparing MCMC posterior distributions for "control" versus "mutant") would be in this case. I'd appreciate help on some sort of a statistic which I could use to arrive at something akin to a $p$-value. Thanks in advance.

$\endgroup$
1
$\begingroup$

Turns out the differences were approximately normally distributed, so I could fit Gaussians to them and perform a t-test. In the end, however, I decided to use a logistic normal prior instead of a Dirichlet based on http://andrewgelman.com/2009/10/21/some_practical/.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.