# Linear first stage, non-linear second stage 2SLS regression

I was wondering if it's possible to perform a 2SLS regression where I first run a regression for my endogenous variable, obtain the predicted values and then use them in my second stage regression (a logit)?

Would this approach yield consistent estimators?

• In general yes, you get a consistent estimator. But there are more efficient ways to obtain the estimates (which are more advanced) Sep 7, 2016 at 18:43
• Hi Repmat, what would these more consistent estimation methods be? Many thanks for the reply! Sep 7, 2016 at 20:35

2. Use logit to regress your $Y$ variable on the predicted values and the exogenous covariates.