For context, I'm using the Andersen healthcare utilization model, specifically focusing on the three "panels" of predisposing, enabling, and need. Each panel has its own associated variables in it, and researchers often use it to see how each panel (+items within the panel) are associated with each other and how they relate to the impact of healthcare service utilization.

I read several papers related to using this model, and everyone had different approaches. Some used hierarchical multiple regression with each panel being used as a "step". Some used logistic regression analyses along with bivariate analyses. The variables/items I'm including are a mix, and this includes categorial variables (male/female) along with scale items (e.g., rate your health status from low to high). I'm also looking to see how migration status, ethnic group, and gender play a role. My dependent variable will basically be if they have gone to a healthcare provider or not.

  • $\begingroup$ Could you please give some more info on your data? And maybe reference/link some of the papers you read? But, if you want to model if they have seen a hp or not, maybe logistic regression ... is a good starting point. $\endgroup$ – kjetil b halvorsen Nov 22 at 15:10

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.