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

From |
Steven Samuels <sjhsamuels@earthlink.net> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: GLLAMM and weights |

Date |
Sat, 13 Dec 2008 22:12:10 -0500 |

-Steve On Dec 13, 2008, at 9:52 PM, Steven Samuels wrote:

I haven't tried this in GLLAMM, so I'm not sure what goes wrongwhen you add the weights. Check that your version of -gllamm- is up-to-date. As requested in the Statalist FAQ, show exactly what youtyped and what Stata produced. It is good practice, as others havepointed out, to start with the simplest model possible (e.g. nocovariates) and try progressively more complex models (e.g. addtreatment) to see where the problem starts. You probably have notrescaled the weights as the GLLAMM manual suggests. See: http://www.stata.com/meeting/4nasug/Chantala.ppt and http://www.cpc.unc.edu/restools/data_analysis/ml_sampling_weights. Thesecontain links to the Stata program -pwigls- which will scale theweights. Rabe-Hesketh and Skrondal (2006) compute the "Method 1"weights by hand and illustrate an analysis in GLLAMM. Try toreplicate their results.-SteveRabe-Hesketh, S. & Skrondal, A. (2006). Multilevel modelling ofcomplex survey data. Journal of the Royal Statistical Society:Series A (Statistics in Society), 169(4), 805-827.On Dec 13, 2008, at 2:06 PM, Ariel Linden wrote:I posted a question a couple weeks ago about using multipleweights perperson/period data (that is, using a different weight per personfor eachperiod). The problem was that xtgee will not accept differentweights perperson.One suggestion that was provided was to use GLLAMM. I triedthat and themultiple weights were indeed accepted by the model. However,another issuepresented itself. I am using 3 variables for the fixed effects;wave, treatment (dummy 1/0),and wave * treatment (for growth). Unfortunately, the model dropsboth thewave and wave * tx variables. This does not happen when I run anunweighted model, nor when I run thisusing regress or glm. Of course, I need both those variables inthe model.* * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

* * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**References**:**st: GLLAMM and weights***From:*Ariel Linden <ariel.linden@gmail.com>

**Re: st: GLLAMM and weights***From:*Steven Samuels <sjhsamuels@earthlink.net>

- Prev by Date:
**Re: st: GLLAMM and weights** - Next by Date:
**Rép. : st: Re: Results displayed in parentheses after -matrix-** - Previous by thread:
**Re: st: GLLAMM and weights** - Next by thread:
**Re: st: GLLAMM and weights** - Index(es):

© Copyright 1996–2016 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |