Statalist


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

RE: st: RE: clustering option after ivprobit


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: RE: clustering option after ivprobit
Date   Tue, 2 Sep 2008 16:41:32 +0100

Thanks to Partha for the correction. Even my second reading of the help
was not careful enough! Do as I say, not as I do....

Nick 
n.j.cox@durham.ac.uk 

Partha Deb

Nick was correct the first time.  -vce(cluster <clustervar>)- is not an 
allowed option along with -twostep- .  It would work if you did not
specify 
-twostep- ,i.e., the -mle- option.

Nick Cox wrote:
> Yes, and sorry: 
> 
> You are correct in that -vce(cluster <clustervar>)- is one allowed
> syntax. 
> So your second example on the face of it should work. Your first
doesn't
> satisfy. 
> 
> I can't explain why not. I hope somebody else can help further. 
> 
> Choudry T Shehzad
> 
> Thanks Nick:
>  In help file for ivprobit, they do ask for cluster variable but even
> without that stata says "vcetype 'cluster' not allowed"
>  
> ivprobit dependent x y l.z (zz = mz pz), vce(cluster) twostep first
> vcetype 'cluster' not allowed
> r(198);
> 
>  ivprobit dependent x y l.z (zz = mz pz), vce(cluster country )
twostep
> first
> vcetype 'cluster' not allowed
> r(198);
> 
> Nick Cox wrote:
> 
>> Typically options belong together after a single comma, for example: 
>>
>> ivprobit dependent x y l.z  (zz = mz pz), vce(cluster) twostep first
>>
>> There are exceptions to that rule but they don't make your syntax
> legal.
>>
>> Beyond that you just have to read the help! For example, for
> -ivprobit-
>> the allowable syntax is just to specify a vcetype; nothing is said
> there
>> about a cluster variable. 
>>
>> Choudry T Shehzad
>>
>> In stata help pages vce(cluster, clustervariable) and vce (bootstrap)
>> has been mentioned as options but when I try to run it says
>>
>>  ivprobit dependent x y l.z  (zz = mz pz), vce(cluster, country),
>> twostep, first
>> invalid 'twostep'
>> r(198);
>>
>> . ivprobit dependent x y l.z  (zz = mz pz), vce(cluster, country),
> first
>> invalid 'first'
>> r(198);
>>
>> . ivprobit dependent x y l.z  (zz = mz pz), vce(cluster, country)
>> option country not allowed
>> r(198);
>>
>> . ivprobit dependent x y l.z  (zz = mz pz), vce(boot)
>> time-series operators are not allowed with bootstrap without panels,
> see
>> tsset
>> r(198);
>>
>> Only option it accepts is vce(robust). While I want to bootstrap
>> standard errors on clusters. I understand that ivprobit is not for
> panel
>> then why this option has been given after ivprobit. can anybody help?

*
*   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/



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