Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Richard Williams <richardwilliams.ndu@gmail.com> |
To | statalist@hsphsun2.harvard.edu, statalist@hsphsun2.harvard.edu |
Subject | Re: st: Brant test and goodness of fit(after -oprobit-) with complex survey data |
Date | Wed, 06 Jun 2012 11:42:44 -0500 |
At 03:10 AM 6/6/2012, Maarten Buis wrote:
On Wed, Jun 6, 2012 at 9:13 AM, Sol <ykim.berlin@gmail.com> wrote: > 1. From what I've read, the Brant test of parallel lines assumption can be > tested in Stata with -omodel probit-. The problem is that this command > doesn't work with the -svy- syntax(I get the message "omodel is not > supported by svy with vce(linearized)"). Is there another way the test can > be implemented in Stata? If I remember correctly you can use -gologit2- to get a test for parallel lines and -gologit2- allows svy. You can install -gologit2- by typing in Stata -ssc install gologit2- and you can read more about it here: <http://www.nd.edu/~rwilliam/gologit2/> Hope this helps, Maarten
Correct. You can test individual variables using the -autofit- option. For a global test, similar to Brant, do something like
webuse nhanes2f, clear gologit2 health female black age height weight, svy test [#1 = #2 = #3 = #4] If you weren't using svy, you could do a LR chi-square test, e.g. gologit2 health female black age height weight, pl sto(ologit) gologit2 health female black age height weight, npl sto(gologit) lrtest ologit gologit, statsMaarten and I did some simulations a few years ago where we compared brant, omodel, and gologit2. All performed about the same, at least in our simulations. brant appeared to be the best. omodel tended to not reject the null often enough, brant was about right, gologit2 rejected a little too often. gologit2 is the only approach I know of when data are svyset. gologit2 also supports several different link functions.
If you have a data set that uses some of the svyset options introduced after Version 9 of stata, I have a beta version of gologit2 that can handle them. Write me off-list for details.
------------------------------------------- Richard Williams, Notre Dame Dept of Sociology OFFICE: (574)631-6668, (574)631-6463 HOME: (574)289-5227 EMAIL: Richard.A.Williams.5@ND.Edu WWW: http://www.nd.edu/~rwilliam * * 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/