How can I get MLE for a custom model?

rdale8250 — Sun, 29 May 2016 06:55:40 GMT

I'm new to JMP so sorry if this is simple. I've read the user manual over and over and cant find the info I need.

I want to find parameters for a custom distribution ideally, or at least use the exponential distribution. Then I want to use it to get MLE for some custom models. I found that I can get MLE with exponential distribution using the "fit model" option and "generalized regression", but I have NO idea how to get it to fit my custom model. I figured out how to fit a simple model, like log(variable), but I don't know how to add parameters to the model.

Alternatively, I can fit my custom model using "nonlinear model" fitting option, but not using MLE on my chosen distribution.

Help please?

Re: How can I get MLE for a custom model?

michael_jmp — Thu, 02 Jun 2016 18:12:30 GMT

Hello,

Thanks for using JMP.

I think you should be able to use the Nonlinear platform to fit a custom model. Here's an example of using the Nonlinear platform to fit a logistic regression model: Logistic Regression Example in Nonlinear

The Nonlinear platform fits models by maximizing the likelihood function, so it is providing an MLE solution.

Hope that helps,

Michael

topic Re: How can I get MLE for a custom model? in Discussions

How can I get MLE for a custom model?

Re: How can I get MLE for a custom model?