可以考虑内省转换模型,参见这两篇paper:Maximum likelihood estimation of endogenous switching regression models;Impact of interventions on discrete outcomes: Maximum likelihood estimation of the binary choice models with binary endogenous regressors
几个方向:1. 就用 ivprobit。2. https://www2.bc.edu/arthur-lewbel/。This folder contains papers, Stata, and Gauss code on Special Regressor and simple binary choice estimation methods, including introductory and survey material: special-regressor-papers-and-code.zip This includes the Stata module SSPECIALREG. 3. 请试试 cmp。https://www.stata-journal.com/article.html?article=st0224。