Re: st: Storing regression coefficient estimates

["Braunfels, Philipp (Stud. SBE / Alumni)" <P.Braunfels@student.maastrichtuniversity.nl>]

Thanks Roger for the Hint. Is there anywhere a document that explains how to use -parmest- I have been searching for the last couple of hours and could not find any. I appreciate your help!

On Fri, Jul 20, 2012 at 12:44 PM, Roger B. Newson <r.newson@imperial.ac.uk> wrote:
> This looks like a job for the -parmest- package, which is downloadable from
> SSC, and which stores regression coefficients in output datasets (or
> resultssets). These resultssets can then be concatenated, subsetted and
> plotted in whatever way the user needt to do.
>
> I hope this helps.
>
> Best wishes
>
> Roger
>
>
> Roger B Newson BSc MSc DPhil
> Lecturer in Medical Statistics
> Respiratory Epidemiology and Public Health Group
> National Heart and Lung Institute
> Imperial College London
> Royal Brompton Campus
> Room 33, Emmanuel Kaye Building
> 1B Manresa Road
> London SW3 6LR
> UNITED KINGDOM
> Tel: +44 (0)20 7352 8121 ext 3381
> Fax: +44 (0)20 7351 8322
> Email: r.newson@imperial.ac.uk
> Web page: http://www.imperial.ac.uk/nhli/r.newson/
> Departmental Web page:
> http://www1.imperial.ac.uk/medicine/about/divisions/nhli/respiration/popgenetics/reph/
>
> Opinions expressed are those of the author, not of the institution.
>
>
> On 20/07/2012 11:21, Braunfels, Philipp (Stud. SBE / Alumni) wrote:
>>
>> Dear Statlisters,
>> I have an unbalanced panel dataset and want to do a two-stage regression.
>> I want to run individual (by panelvar) time series regressions (rolling
>> time frame) and store the estimates of each coefficient in a new variable.
>> With "rolling time frame" I mean that the coefficients in period t are
>> estimated based on values from period t-24 to t (that is, on the prior 24
>> months of data).
>>   My set starts in month 476 and contains 120 months of data. My approach
>> looks as follows but I just do not get how to store the estimates and define
>> the correct time frame (according to "help reg" the coefficients are stored
>> in a vector e(b)):
>>
>> [ID= panelvar, month=timevar]
>>
>> gen beta_x1=0
>> gen beta_x2=0
>> gen beta_x3=0
>> gen intercept=0
>>
>> *define time frame
>> forvalues i=500/596{
>>
>> *define separate regressions for each firm in my panel
>> quietly levelsof ID ,l(lvls)
>> foreach l of loc lvls {
>>      quietly reg y x1 x2 x3, vce(robust) if (ID == "`l'" & month>`i'-24 &
>> month<`i'+1), vce(robust)  **** -& month>`i'-24 & month<`i'+1- is intended
>> to capture the rolling window of 24 months
>>
>> *store coefficients
>>      replace beta_x1= "coefficient_x1" if (ID == "`l'" & month==`i'+1)
>>      replace beta_x2="coefficient_x2" if (ID == "`l'" & month==`i'+1)
>>      replace beta_x2="coefficient_x3" if (ID == "`l'" & month==`i'+1)
>>      replace intercept="_constant" if (ID == "`l'" & month==`i'+1)
>> }
>> }
>>
>>   Can someone help me
>> (i) how do I correctly specify that the regression is estimated for a
>> rolling window of 24 months (which I did above by writing -& month>`i'-24 &
>> month<`i'+1-) , i.e. the coefficients for month 501 are estimated based on
>> the values from months 476-500, the coefficients for 502 are estimated from
>> months 477-501 and so on...
>>   (ii) how can I specify that only the coefficient of x1, x2 or x3 is
>> stored (I just wrote "coefficient_x#")
>>
>> I am very very thankful for any help and greatly appreciate your time!
>> *
>> *   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/

*
*   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/