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

From |
Buzz Burhans <wsb2@cornell.edu> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
st: xtmixed multilevel fixed effects? |

Date |
Thu, 05 May 2005 09:50:46 -0400 |

Am I correct in thinking that -xtmixed- enables use of random effects at a level 1 if a two level model, but not fixed effects at level 1? i.e. Can I have fixed effects at more than one level of a multilevel model using xtmixed? For instance, in the example 5, pg 191 of the Longtitudinal/Panel manual, where the equation "xtmixed gsp......|| region: hwy unemp || state:...." appears, is it possible to have a predictor at the "region" level that does not appear as a fixed effect in the fixed effect equation for gsp ~ ? For instance, suppose I wanted the term "railroads" at the region level only? Or alternately, suppose I want hwy and unemp as predictors for region, but not random effects of the fixed terms hwy and unemp?

Buzz Burhans

Buzz Burhans

wsb2@cornell.edu

*

* 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: RE: Stata 9: first impressions?***From:*David Airey <David.Airey@vanderbilt.edu>

- Prev by Date:
**Re: st: Stata 9: first impressions?** - Next by Date:
**st: RE: diagnostic tests after fe regression** - Previous by thread:
**st: RE: Stata 9: first impressions?** - Next by thread:
**st: Time Format** - Index(es):

© Copyright 1996–2015 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |