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

From |
David Airey <david.airey@Vanderbilt.Edu> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: xtmelogit |

Date |
Mon, 18 Aug 2008 09:25:11 -0500 |

.

Subscribing is one solution, sure.

Given that xtmelogit is limited to binary dependent variables, I'd guess you were right about different field's use of logit model terminology. Certainly mine. Thanks for explaining.

I have used GLLAMM for a mixed multinomial logit model (multiple isoform edited RNAs sampled from mice); I'll try your program. Thanks.

-Dave

On Aug 18, 2008, at 9:02 AM, Arne Risa Hole wrote:

I think Dave's criticism is partly related to different terminology being used in different disciplines. In economics the term 'mixed logit' is most often used to refer to a mixed/multilevel/random-coefficients/random-parameters logit model with two or more alternatives but that may not be the case in other fields. Having said that I agree that the abstract of my paper could be more informative. I think the capabilities of -mixlogit- are understandable from the paper's introduction but that is of course not accessible to non-subscribers (at least not yet). Arne On 18/08/2008, David Airey <david.airey@vanderbilt.edu> wrote:.

I would not have guessed that mixlogit fit multilevel multinomial models

from the abstract supplied by the author.

"This article describes the mixlogit Stata command for fitting mixed logit

models by using maximum simulated likelihood."

One criticism I have of the Stata-Journal is that the editors should

encourage more detailed abstracts, even from command articles and tip

articles.

-Dave

On Aug 18, 2008, at 6:22 AM, Arne Risa Hole wrote:

And I should also say that -mixlogit- is available from the SSC archive... Those who are interested may want to take a look at the paper describing the command which was published in Stata Journal 7(3). 2008/8/18 Arne Risa Hole <arnehole@gmail.com>:Thanks to Jay for the plug - the program is called -mixlogit-. Arne 2008/8/13 jverkuilen <jverkuilen@gc.cuny.edu>:"Changwoo Lee" <pfak2121@bu.edu> wrote:I wonder if I can use xtmelogit or xtlogit for the multinomial logit

withrandom intercepts. Please let me know.>

You want -gllamm- or another user-supplied program the name of which

eludes me now, but the author's name is Arne Rise Hole.* * 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/* * 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/

**Follow-Ups**:**Re: st: xtmelogit***From:*"Arne Risa Hole" <arnehole@gmail.com>

**References**:**RE: st: xtmelogit***From:*jverkuilen <jverkuilen@gc.cuny.edu>

**Re: st: xtmelogit***From:*"Arne Risa Hole" <arnehole@gmail.com>

**Re: st: xtmelogit***From:*"Arne Risa Hole" <arnehole@gmail.com>

**Re: st: xtmelogit***From:*David Airey <david.airey@Vanderbilt.Edu>

**Re: st: xtmelogit***From:*"Arne Risa Hole" <arnehole@gmail.com>

- Prev by Date:
**Re: st: Problem with ARIMA-ARCH model** - Next by Date:
**Re: st: RE: RE: Bootstrap and Technical analysis** - Previous by thread:
**Re: st: xtmelogit** - Next by thread:
**Re: st: xtmelogit** - Index(es):

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