1
$\begingroup$

If I have fitted training data to a probability distribution, e.g. a poisson distribution, how can I test this fit on some test data?

To fit the poisson distribution I am using R's fitdistrplus package that using MLE for determining the optimal coefficients of a given distribution. Therefore, I have the estimated $\lambda$ for a poisson distribution based on my training data but I am not sure how to test this on some unseen test data.

$\endgroup$
3
4
$\begingroup$

Use chi-square test to check the goodness of fit to a specific distribution http://courses.wcupa.edu/rbove/Berenson/10th%20ed%20CD-ROM%20topics/section12_5.pdf

$\endgroup$
2
  • $\begingroup$ I read over the notes and the chi-square test determines whether or not a poisson distribution is an appropriate fit to the data, but it does not help me compare several poisson distributions that are fit to the same data. Know any way I can compare these? $\endgroup$ – guy Dec 29 '17 at 14:23
  • $\begingroup$ Hi guy, I think this post answers your question link $\endgroup$ – Yang Song Dec 29 '17 at 18:44

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.