Re: [SPAM] RE: st: RE: svy probit/logit iv

[Richard Williams <Richard.A.Williams.5@ND.edu>]

At 01:34 PM 7/12/2006, Zhu, Liye wrote:
> Thanks for Professor Williams' answer!
>
> When I use -suest ml, svy- after -ivprobit- and -est store-, the 
> error message is "option svy not allowed, r(198);". I already did 
> -svyset [pweight=wtper2], strata(stratawr) psu(psuwrx)-. I am using Stata 9.2.
Liye, I suggest running this example I provided earlier:

webuse nhanes2f
ivprobit diabetes female (heartatk = rural) [iw=finalwgt]
est store m1
suest m1, svy

If you get an error message, then I suspect your Stata installation 
has problems, e.g. your ado files may not be up to date.

If my example does run, I would suggest posting your code and 
output.  My guess is you are typing something wrong or are not 
properly svysetting the file, but it is impossible to tell without 
seeing what you actually did.  Indeed, if that is the way you typed 
in the svyset command, it looks wrong to me; I think it should be

svyset psuwrx [pweight=wtper2], strata(stratawr)


> Another question: how do you choose iweight in -ivprobit-? In my 
> case, the survey data only provides one weight variable, which is 
> recommended by the codebook to be used as "svyset [pweight=wtper2], 
> strata(stratawr) psu(psuwrx)". Since there is no other weight 
> variable, in -ivprobit-, I set [iweight=wtper2]. I am not quite sure 
> if this is where the problem comes from.
See my above example.

> Question about -suest-: From Stata 9.2 help file, "The within-model 
> covariance matrices computed by suest are identical to those 
> obtained by specifying a robust or cluster() option during 
> estimation.  suest, however, also estimates the between-model 
> covariances of parameter estimates.". Since I am using -ivprobit-, 
> does this mean there is any between-model covariances of parameter 
> estimates? If not, then the ways to use -suest- and to specify 
> robust or cluster() option during estimation are identical. right?
The above refers to when you are estimating 2 or more models.  You 
might do this if, say, you wanted to test equality of coefficients 
across models.  You are only doing one estimation in this case.

If using suest, you should not also specify robust and cluster.  Like 
the help for suest says, "Estimation should take place without the 
options robust or cluster().  suest always computes the robust 
estimator of the (co)variance, and suest has a cluster() option."

The whole reason you are using suest in the first place is because 
robust and cluster aren't enough, i.e. they don't capture the effects 
of your stratification variable.



> Last question about score: it seems that Stata 9.2 considers score 
> as old. So commands in Stata 9.2, such as -ivprobit-, do not 
> surpport score. I do not need to specify score in -ivprobit-. 
> Correct? By the way, I am not familiar with the score option.
No, you don't need to specify it in Stata 9.  Suest will take care of 
this for you.  Again, you can use my example as a template for your 
own analysis.


-------------------------------------------
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/