Quasi-Maximum Likelihood based Model Selection Procedures for Binary Outcomes

06/14/2021

∙

by   Shunichiro Orihara, et al.

∙

0

∙

share

In this paper, I propose two model selection procedures based on a quasi-maximum likelihood estimator when there exist unmeasured covariates. I prove that a proposed BIC-type model selection procedure has model selection consistency, and confirm these property through simulation datasets.