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: Questions about selmlog and svyselmlog
From
"Yu(Sophia) Zhang" <[email protected]>
To
[email protected]
Subject
Re: st: Questions about selmlog and svyselmlog
Date
Thu, 21 Oct 2010 14:52:34 -0400
Dear Joao,
Thanks for your prompt reply.
The correct data structure will make me loose most of the values of
depvar. What's your comments on this? Do I need to run 3 seperate
selmlog regression?
Thanks
Yu
On Thu, Oct 21, 2010 at 2:45 PM, Joao Ricardo F. Lima
<[email protected]> wrote:
> Yu,
>
> your data structure is wrong. This is the correct way:
>
>> depvar varlist, select ( depvar_m = varlist_m)....
>>
>> 500 x 1 z
>> 456 x 1 z
>> 529 x 1 z
>> 601 x 1 z
>> . x 2 z
>> . x 2 z
>> . x 2 z
>> . x 3 z
>> . x 3 z
>> . x 3 z
>> . x 3 z
>> . x 3 z
>>
>
> Joao Lima
>
>
> 2010/10/21 Yu(Sophia) Zhang <[email protected]>:
>> Dear Joao,
>>
>> Thanks for your patient explanation. I thought I understood what
>> you mean. But when I followed the rule and made sure that the
>> dependent variable has non-missing values for only one category, the
>> same error still showed up.
>>
>> What I understand the correct data structure about missing values
>> of depvar is like this:
>>
>> depvar varlist, select ( depvar_m = varlist_m)....
>>
>> 500 x 1 z
>> 456 x 1 z
>> 529 x 1 z
>> 601 x 1 z
>> miss x 2 z
>> 547 x 2 z
>> 408 x 2 z
>> 620 x 3 z
>> 599 x 3 z
>> 512 x 3 z
>> miss x 3 z
>> miss x 3 z
>>
>> So the depvar has non-missing values for category 1 only. It has
>> missing values for all the other categories (2 and 3).
>>
>> Would you please kindly correct me if I am wrong?
>>
>> I appologize to ask another question. If the command works, how
>> could save the variable lambda (Heckman correction term)?
>>
>> I appreciate your help a lot!
>>
>> Yu
>>
>>
>>
>>
>> On Wed, Oct 20, 2010 at 11:08 AM, Joao Ricardo F. Lima
>> <[email protected]> wrote:
>>> Dear Yu,
>>>
>>> the sintax of selmlog is:
>>>
>>> selmlog depvar varlist, select(depvar_m=varlist_m) [lee dmf(#) dhl(# [all]) etc
>>>
>>> depvar_m is your categorical variable, with more than 2 categories, oks?
>>>
>>> and
>>>
>>> depvar must have non-missing values for only one of theses categories.
>>>
>>> HTH,
>>>
>>> JL
>>>
>>>
>>>
>>> 2010/10/20 Yu(Sophia) Zhang <[email protected]>:
>>>> Dear Joao,
>>>>
>>>> Thanks so much for your reply. The second question has been solved
>>>> following your suggestion.
>>>>
>>>> For the first one, do you mean that across all categories ( which
>>>> are schools in my selection equation), only one category can have
>>>> non-missing values of dep var, and the other categories must have some
>>>> missing values of depvar? I deleted some values of depvar to meet this
>>>> requirement, but I still got the same error. Would you mind explaining
>>>> it in more detail?
>>>>
>>>> Thank you so much!
>>>>
>>>> Yu
>>>>
>>>> On Tue, Oct 19, 2010 at 7:03 PM, Joao Ricardo F. Lima
>>>> <[email protected]> wrote:
>>>>> Yu,
>>>>>
>>>>> About the first question:
>>>>>
>>>>> The vardep of the income equation must have non missing values ONLY
>>>>> for one category.
>>>>>
>>>>> About the second:
>>>>>
>>>>> the svyselmlog was written to Stata 8. Then, try this:
>>>>>
>>>>> version 8: svyset [pweight = varw], psu(varpsu) strata(varstrat)
>>>>> svyselmlog vardep varindep , sel() meth() boot()....
>>>>>
>>>>> Hope this Helps,
>>>>>
>>>>> Joao Lima
>>>>>
>>>>>
>>>>> 2010/10/19 Yu(Sophia) Zhang <[email protected]>:
>>>>>> Dear statisticians,
>>>>>>
>>>>>> I am now working on my dissertation and am stuck by a STATA command.
>>>>>> Basically, I want to run Heckman correction based on the multinomial logit
>>>>>> model. I am going to use the command selmlog. However, a strange error shows
>>>>>> up like this:
>>>>>>
>>>>>> Non-missing values of dependent variable for more than one outcome
>>>>>> variable _m* not found
>>>>>>
>>>>>> I guess it might be associated with this statement in the help file:
>>>>>>
>>>>>> 1) In the output, selmlog adds to varlist a series of variables labelled
>>>>>> _m[depvar_m value], except for the dhl option
>>>>>>
>>>>>> 2) The outcome variable depvar is observed for only one value of depvar_m.
>>>>>> It is important that depvar should have missing values for any other value
>>>>>> of depvar_m.
>>>>>>
>>>>>> But still cannot figure out what's wrong.
>>>>>>
>>>>>> In addition, when I want to control for sampling weights by running the
>>>>>> command svyselmlog, I get another error:
>>>>>>
>>>>>> data not set up for the old survey estimation commands; use svyset under
>>>>>> version control or use the new svy prefix.
>>>>>>
>>>>>> But there is no "svy: selmlog" command in STATA 11.....
>>>>>>
>>>>>> I wonder if someone could kindly give me some hint for these two
>>>>>> problems. I have asked several people but no one were familiar with this
>>>>>> problem.
>>>>>>
>>>>>> I appreciate your help very much.
>>>>>>
>>>>>> Sincerely,
>>>>>>
>>>>>> Yu
>>>>>>
>>>>>> *
>>>>>> * 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/
>>>>>>
>>>>>
>>>>>
>>>>>
>>>>> --
>>>>> ---------------------------------------------------------
>>>>> João Ricardo F. de Lima
>>>>> Pesquisador A - Economia Aplicada
>>>>> Embrapa Semiárido
>>>>> e-mail: [email protected]
>>>>> fone: +55 (87) 3862-1711 Ramal: 167
>>>>> home-page: www.cpatsa.embrapa.br
>>>>> ----------------------------------------------------------
>>>>>
>>>>> *
>>>>> * 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/
>>>>>
>>>>
>>>>
>>>>
>>>> --
>>>> Yu Zhang
>>>> PhD Candidate
>>>> Economics and Education
>>>> Teachers College, Columbia University
>>>>
>>>> *
>>>> * 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/
>>>>
>>>
>>>
>>>
>>> --
>>> ---------------------------------------------------------
>>> João Ricardo F. de Lima
>>> Pesquisador A - Economia Aplicada
>>> Embrapa Semiárido
>>> e-mail: [email protected]
>>> fone: +55 (87) 3862-1711 Ramal: 167
>>> home-page: www.cpatsa.embrapa.br
>>> ----------------------------------------------------------
>>>
>>> *
>>> * 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/
>>
>> *
>> * 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/
>>
>
>
>
> --
> ---------------------------------------------------------
> João Ricardo F. de Lima
> Pesquisador A - Economia Aplicada
> Embrapa Semiárido
> e-mail: [email protected]
> fone: +55 (87) 3862-1711 Ramal: 167
> home-page: www.cpatsa.embrapa.br
> ----------------------------------------------------------
>
> *
> * 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/
>
--
Yu Zhang
PhD Candidate
Economics and Education
Teachers College, Columbia University
*
* 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/