[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
David Jacobs <jacobs.184@osu.edu> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: dep. var. with zeros and fixed effect (or cluster) estimation[trim. least squares?] |

Date |
Tue, 18 Feb 2003 13:18:27 -0500 |

You don't tell us enough to answer your question. If the variable in question is continuous and arguably normally distributed at least in the population, a version of Tobit called "intreg" should work because the robust and cluster options are available for this command.

If this dependent variable is a count with a modest mean either Poisson, negative binomial, or the zero inflated versions of those two commands would be appropriate. If you are analyzing repeated measures for the same case and/or you want to do a a pooled time-series cross-sectional panel analysis, Stata has panel versions of tobit, intreg, poisson and negative binomial. Stata does not have panel versions of zero inflated count models, but Limdep (another program) might. Of course, since Stata doesn't offer fixed effects tobit or intreg estimators, you will have to use random effects or population averaged estimation to employ a panel analysis using tobit or it's derivatives.

Dave Jacobs

At 06:16 PM 2/17/2003 -0800, you wrote:

Hello everyone, I am writing because I was wondering what procedure I could use in STATA or other statistical software to analyze a dependent variable that has many zeros, if at the same time I want to use fixed effects or clustering in the regression equation (because it is a very short [i.e. 2-period] panel). The fixed effects or clustering does not allow one to use Tobit. I saw a reference somewhere to symmetrically trimmed least squares for this situation. Any ideas how I could do his or an alternative estimation for this problem? Thank you for your help, matt __________________________________________________ Do you Yahoo!? Yahoo! Shopping - Send Flowers for Valentine's Day http://shopping.yahoo.com * * For searches and help try: * http://www.stata.com/support/faqs/res/findit.html * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

* * For searches and help try: * http://www.stata.com/support/faqs/res/findit.html * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**References**:**st: dep. var. with zeros and fixed effect (or cluster) estimation [trim. least squares?]***From:*Matias Barenstein <barenmat@yahoo.com>

- Prev by Date:
**st: RE: ancova?** - Next by Date:
**st: False negatives in clinical work** - Previous by thread:
**st: dep. var. with zeros and fixed effect (or cluster) estimation [trim. least squares?]** - Next by thread:
**st: quietly bug** - Index(es):

© Copyright 1996–2014 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |