I am new here and am trying to build and compare a couple models using spatial data for estimation (GLM and GWR). I am trying to estimate counts using a training dataset that contains observations on randomly located points across the study area. At the moment, I am using three independent variables with metrics that describe the counting points.

On the other hand, I have some aggregated census attributes that I could assign (join) to the points based on the census area.

Here is my question, would it be appropriate to use a GWR model in this case?

I am new to spatial statistics. I understand that the predictive capabilities of GWR are limited. Am I correct? I would appreciate some guidance.

Thanks for your time.

New contributor
Juan P FZ is a new contributor to this site. Take care in asking for clarification, commenting, and answering. Check out our Code of Conduct.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.