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 |
Stas Kolenikov <skolenik@gmail.com> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: GLLAMM question |

Date |
Wed, 28 Mar 2012 21:21:12 -0500 |

Alexandra, this looks like a job for -margins- command. Study the help file and examples to fine tune it to your problem at hand. It may be as simple as margins MyImportantDummy probably with -atmeans- option. On Tue, Mar 27, 2012 at 9:41 AM, Alexandra Mahler-Haug <alexandra.mahlerhaug@gmail.com> wrote: > Using a gllamm model, I am trying to estimate the resulting > probabilities that my dichotomous dependent variable==1 from changing > the value of one dichotomous independent variable (setting the value > of the independent variable in question at "1" and "0") while holding > all other of my independent variables at their means/modes. > > Previously in my research, I used a one-level logit model in Stata and > CLARIFY to estimate the change in probability (that my dichotomous > dependent variable==1) which resulted from changing a dichotomous > independent variable from 1 to 0 (while setting all other independent > variables at their means/modes). > > However, the gllamm model is not supported by Clarify. I believe that > there may be another way through Stata to set the values of > independent variables at different levels and then compute the > resulting probabilities that the dichotomous dependent variable==1 > (under the estimated parameters of the gllamm model). I have not used > gllapred or gllasim, but both of those appear to not offer an option > to "set" the values of the independent variables (setting one > independent variable at 0 and then 1 while also setting all other > independent variables at their means/modes) and then calculate the > probability that the dependent variable==1. > > I hope my question is understandable - any information/guidance would > be much appreciated! > > All the best, > Alexandra Mahler-Haug > > * > * 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/ -- Stas Kolenikov, also found at http://stas.kolenikov.name Small print: I use this email account for mailing lists only. * * 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 question***From:*Alexandra Mahler-Haug <alexandra.mahlerhaug@gmail.com>

- Prev by Date:
**Re: st: RE: Diagnostic results of ivreg2** - Next by Date:
**st: base alternative in asclogit** - Previous by thread:
**st: GLLAMM question** - Next by thread:
**st: work with larger string length** - Index(es):