GLM with growth function - problem of indetermiinability when slope = 0

[stijn]

Martin discusses this problem in his blog post on identifiability and divergences.

Blog post: Identifying non-identifiability

Hi all, I wrote a blog post, surveying some broken models in hope it helps people spot, uncover and understand issues with their models. http://www.martinmodrak.cz/2018/05/14/identifying-non-identifiability/ As in the previous post about divergences, I am learning this stuff as I go, so feedback is very welcome, hopefully I didn’t get anything very wrong.

In the same thread, I suggest one (unprincipled and untested) way to constrain the beta parameter.

Blog post: Identifying non-identifiability

This is really cool. In the spirit of giving back. The problem you identify in the sigmoid model with non-identified special case made me think of the problem with multi-collinearity. That is, a parameter blowing up because of near non-identifiability. In one of Andrew Gelman’s papers there was some suggestion to solve that with a sort of joint prior for some of the parameters. I had some success with taming divergences in that way but I have no idea whether there are any problems with the appro…