We will need to use a special database named card.dta that you can download from: ![]() For a review of the theory, please check Green or Wooldridge’s books. That is why we need to find another variable, called an instrument, that is exogenous and it is correlated with the outcome variable only through its effect on the endogenous regressor. When you have an endogenous regressor, your OLS estimates become inconsistent and it may happen thanks to measurement error or omitted variable biases. ![]() ![]() Today we are going to study a group of variables that I personally dislike: endogenous one. Sometimes your variable are not good enough to predict an outcome and you need to find a replacement to instrument them.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |