Notice: On March 31, it was **announced** that Statalist is moving from an email list to a **forum**. The old list will shut down on April 23, and its replacement, **statalist.org** is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
Xuan Zhang <xuanzhan@buffalo.edu> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
st: question about two stage least square and ordered probit model |

Date |
Wed, 5 Dec 2012 22:33:41 -0500 |

Dear everyone, I have a question about the 2SLS. My model is like below: y=X'β1+γM+u1 and M is the IV that I will estimated from equation: M=X'b+u2 However the M variable is a dummy variable which could be 1 2 3 4. So in the estimation of M, I plan to use a ordered probit model. Then substitutes the estimation into the first equation to get β1. I'm not sure how could I deal with the problem in STATA. I read some materials regarding this issue. I suppose I should use smm. But I'm not sure whether I'm in the right direction. My second question is: if I could solve the problem, could I apply it into panel data. I'm now using a cross section data. Thanks a lot. Best, Xuan Zhang Department of Economics, SUNY Buffalo * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/

- Prev by Date:
**Re: st: Too many macros, but I create 1!** - Next by Date:
**Re: st: Average coefficient of data sets** - Previous by thread:
**st: Average coefficient of data sets** - Next by thread:
**st: Intraclass correlation coefficient biased if number of clusters is small?** - Index(es):