Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Heteroskedasticity logit model
From
Richard Williams <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: Heteroskedasticity logit model
Date
Wed, 11 Dec 2013 11:24:02 -0500
The hetero model is supposed to be a solution for dealing with hetero, not just a means of detecting it. How it works, and how well, are discussed in the materials I sent earlier.
Sent from my iPad
> On Dec 11, 2013, at 10:12 AM, Nerissa Fanoembi <[email protected]> wrote:
>
> Thanks for your help.
>
> The hetprob shows a problem of heteroskedasticity.
> Do you know how to solve hetero in the logit model then?
>
> ----------------------------------------
>> Date: Wed, 11 Dec 2013 09:44:49 -0500
>> To: [email protected]; [email protected]
>> From: [email protected]
>> Subject: Re: st: Heteroskedasticity logit model
>>
>> The user-written -oglm- routine available at SSC can estimate ordinal
>> and binary hetero models using logit, probit, and other links. There
>> are various controversies concerning such models. See, for example,
>>
>> http://www3.nd.edu/~rwilliam/xsoc73994/RW_ESRA2013.pptx
>>
>> and the sources it cites. The oglm support page is at
>>
>> http://www3.nd.edu/~rwilliam/oglm/index.html
>>
>> Incidentally, I would probably just go ahead and use hetprob unless
>> you really need the other features that oglm offers.
>>
>> At 06:47 AM 12/11/2013, Nerissa Fanoembi wrote:
>>> Hello,
>>> I am running a pooled logit model. The data is randomly sampled
>>> cross sections from 2004 till 2012. I want to check the
>>> heteroskedasticity problem. But there is no heteroskedasticity test
>>> available for the logit model. How is it possible to test
>>> heteroskedasticity then? The probit model is almost similar as the
>>> probit model. Therefore I run the hetprob command where I include
>>> all independent variables (categorical and continuous independent
>>> variables). The test shows that heteroscedasticity is a problem (the
>>> prob of the Likelihood-ratio test of lnsigma2 is 0.0001). In
>>> addition, what can I do to solve the heteroskedasticity problem in
>>> the logit model? And what is the useful procedure to test
>>> heteroskedasticity in a logit model?
>>> Best regards,
>>> Nerissa Fanoembi.
>>> *
>>> * For searches and help try:
>>> * http://www.stata.com/help.cgi?search
>>> * http://www.stata.com/support/faqs/resources/statalist-faq/
>>> * http://www.ats.ucla.edu/stat/stata/
>>
>> -------------------------------------------
>> Richard Williams, Notre Dame Dept of Sociology
>> OFFICE: (574)631-6668, (574)631-6463
>> HOME: (574)289-5227
>> EMAIL: [email protected]
>> WWW: http://www.nd.edu/~rwilliam
>>
>> *
>> * For searches and help try:
>> * http://www.stata.com/help.cgi?search
>> * http://www.stata.com/support/faqs/resources/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/faqs/resources/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/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/