I have a statistic question concerning the null hypotesis testing in bayesian inference. I red that i can use HPD for testing the null value in a linear bayesian regression:

"We can then use the posterior distribution to discern the credible values of the parameter. If the null value is far from the credible values, then we reject the null value as not credible. But if all the credible values are virtually equivalent to the null value, then we can accept the null value. This intuitive decision procedure is given formal expression in this section."

But i'm reading on papers that in a bayesian approach people use Bayes Factor for hypotesis testing, the question is. Can i simply use the HPD? i used stan and it's easier for me testing with a range of value than computing (how?) a bayes factor.

Can someone help me understanding the difference?


Your Answer

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

Browse other questions tagged or ask your own question.