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

From |
Evans Jadotte <evans.jadotte@uab.es> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
st: [Fwd: Hierarchical model] |

Date |
Fri, 02 Oct 2009 18:26:37 +0200 |

Hello listers!

Thanks! EJ

---Begin Message---

FromEvans Jadotte <evans.jadotte@uab.es> Tostatalist@hsphsun2.harvard.edu SubjectHierarchical model DateFri, 02 Oct 2009 11:26:36 +0200 Dear statalisters,I am estimating a linear three-level hierarchical model via "restrictedmaximum likelihood-REML" with the /xtmixed/ command, with households(level-1) nested into villages (level-2) nested into regions (level-3).Specification seems alright. However, the empirical Bayes randomintercept at level-3, which according to theory should be inferior orequal to the corresponding calculated REML estimate, do not reflect theREML estimate that I calculated at that level. Specifically, I have anempirical Bayes (the BLUP r.e. computed by Stata) that is more than 300times the REML estimate calculated at level-3. At level-2 it seemsreasonable, empirical Bayes = 0.87 REML estimate.Moreover, I expected the sum of the variances (that of raw residuals atlevel-1 + that of residuals REML level-2 + that of residuals REMLlevel-3). When I compute them however, the result gives an estimatedtotal variance that is lower than that of the raw residuals at level-1.I am pretty confident about the model specification and the computationbut evidently things do not match as they should. Can anyone familiarwith these models give me any feedback? I would so much appreciate andthanks in advance.Evans

---End Message---

- Prev by Date:
**Re: st: -collapse- with no observations?** - Next by Date:
**Re: st: Hierarchical model** - Previous by thread:
**st: Indirect and direct marginal effects in recursive biprobit** - Next by thread:
**[no subject]** - Index(es):

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