Re: st: xtmixed, outreg2 and esttab

[Clara Barata <maria_barata@mail.harvard.edu>]

Ups I apologize. The question has just been answered.
Clara

On Wed, Jul 21, 2010 at 2:28 PM, Clara Barata
<maria_barata@mail.harvard.edu> wrote:
> Hi Roy,
>
> Thanks for the extra code. By bad tables I meant that the estimates
> for the same predictor were not aligned in the table, but instead were
> being added to the bottom of the second column (outreg); or the output
> for the two models was being listed sequentially, instead of
> side-by-side (esttab). I am big fan of outreg, but the code you
> propose seems a bit complicated. I am trying to prepare a set of code
> that can be shared with a group of people, some of which are stata
> beginners. Also when i ran what you proposed, i got the message
> "option ststr() not allowed"
>
> . outreg2  using teacher.doc, addstat ("ICC L1", e(rho1), "ICC L2",
> e(rho2),"-2LL",e(ll),"df",e(df_m)) ///
>> bdec(3) alpha(.001, .01, .05, .10) symbol(***, **, *, ~) append  long ///
>> ststr(eqmatch teacher_age ce1p8)
> option ststr() not allowed
>
> Is there a simpler option, maybe using esttab?
>
> Thanks again, Clara
>
> On Wed, Jul 21, 2010 at 1:31 PM, Roy Wada <roywada@hotmail.com> wrote:
>>
>> I don't know what you mean by "bad tables", but this will do the job:
>>
>> * get data
>> sysuse auto, clear
>> ren price teacher_age
>> ren rep78 interv1
>> ren foreign idclase1
>> ren turn idcoleg1
>> ren weight ce1p8
>>
>>  prog drop _all
>> prog define eqmatch
>>  syntax anything
>>  gettoken one two: anything
>>  local one=trim("`one'")
>>  local two=trim("`two'")
>>  split varname, parse(":") gen(_varname)
>>  replace eqname="`one'" if eqname=="`two'"
>>  replace report=eqname+":"+_varname2
>> end
>>
>> xtmixed teacher_age interv1 ||idcoleg1: , cov(un)  ||idclase1:, cov(un) mle
>> var
>> xtmrho
>> outreg2  using teacher.doc, addstat ("ICC L1", e(rho1), "ICC L2", ///
>> e(rho2),"-2LL",e(ll),"df",e(df_m)) ///
>> bdec(3) alpha(.001, .01, .05, .10) symbol(***, **, *, ~) replace long
>>
>> xtmixed ce1p8 interv1 ||idcoleg1: , cov(un)  ||idclase1:, cov(un) mle var
>> xtmrho
>> *stick in the new sub-option using ststr( )
>> outreg2  using teacher.doc, addstat ("ICC L1", e(rho1), "ICC L2", ///
>> e(rho2),"-2LL",e(ll),"df",e(df_m)) ///
>> bdec(3) alpha(.001, .01, .05, .10) symbol(***, **, *, ~) append  long ///
>> ststr(eqmatch teacher_age ce1p8)
>>
>>
>>
>>
>>
>>
>>
>> ________________________________
>> Hotmail has tools for the New Busy. Search, chat and e-mail from your inbox.
>> Learn more.
>
>
>
> --
> M. Clara Barata, Ed.M
> Doctoral student, Human Development and Education
> Harvard Graduate School of Education
> Larsen 705, 14 Appian Way
> Cambridge, MA 02138
>
> Lab phone: 617-496-0535
> Fax: 617-495-3626
> Cell: 857-253-1138
>



-- 
M. Clara Barata, Ed.M
Doctoral student, Human Development and Education
Harvard Graduate School of Education
Larsen 705, 14 Appian Way
Cambridge, MA 02138

Lab phone: 617-496-0535
Fax: 617-495-3626
Cell: 857-253-1138

*
*   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/