Statalist The Stata Listserver


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

Re: st: Re: Fixing an -ml model- syntax problem


From   Richard Williams <Richard.A.Williams.5@ND.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Re: Fixing an -ml model- syntax problem
Date   Tue, 20 Feb 2007 17:41:31 -0500

At 05:19 PM 2/20/2007, Clive Nicholas wrote:
I switched on the -eform- option in -estout- when in fact $\{delta}$ is conventionally measured in log-odds, but it was still -0.20 under -glogit- and 0.20 under -oglm-. However, your solution sorts that out, as well as the fit. Maybe you should incorporate it into the next version of -oglm-, Richard. That leaves my question (2) remaining.
Our messages are crossing here! Yes, I probably could add Allison's delta to the output or include a post-estimation command for it. But, it only applies to a special case, when the heteroskedasticity is believed to involve 2 groups. oglm is much more flexible than that. Personally i think Allison did a great job of presenting the problem but his solution has a number of weaknesses and limitations in it.

As far as your 2nd question goes, I'm not sure if I've now answered it or not. If not, maybe you could rephrase it, since I'm not quite sure what you were asking.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX: (574)288-4373
HOME: (574)289-5227
EMAIL: Richard.A.Williams.5@ND.Edu
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
*
* 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/




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