My problem was not extracting the coefficients, but formatting the
table using listtex.
What I need is to get the standard error in the line below and in
parenthesis, and I don't think that listtex will allow me to do that.
So, what I need is
Dep var. Coef Sample R-squared
Reg 1 0.65 11,224 0.56
(0.05)
and what I am having difficult is getting that (0.05) to appear in the table.
On Wed, Aug 26, 2009 at 2:13 PM, Newson, Roger B<[email protected]> wrote:
> I think you need to use the -el()- function in your -statsby- command to extract multiple items from the same matrix to each observation in the output dataset. The expression
>
> el("e)b)",1,1)
>
> returns the first regression coefficient in the model. And the function
>
> el("e(b)",1,2)
>
> returns the second regresion coefficient in the model. So your -statsby- code might look something like
>
> tempfile tf1
> statsby N=(e(N)) r2=(e(r2)) beta1=(el("e(b)",1,1)) beta2=(el("e(b)",1,2)) , saving(`"`tf1'"', replace) : regress mpg price weight
>
> and this should create a file with 1 observation, and 4 variables -N-, -r2-, -beta1- and -beta2-, containing the sample size, the R-squared, the first regression coefficient, and the second regression coefficient, respectively. (If you were using -parmby- instead of -statsby-, then you would have to use -reshape wide- afterwards to get observations with 2 regression coefficients each.)
>
> 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: [email protected]
> 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.
>
> -----Original Message-----
> From: [email protected] [mailto:[email protected]] On Behalf Of richard boylan
> Sent: 26 August 2009 19:40
> To: [email protected]
> Subject: Re: st: RE: latex table with estimation results reported in rows and coefficient estimates listed in columns
>
> The problem with doing it this way is that the standard error for each
> coefficient has to end up in the same line.
>
> I should have specified that I would want the standard error to be
> below and in parenthesis below each coefficient.
>
> I tried to figure out if there was a way to do that with listtex but
> could not figure it out a way.
>
> On Wed, Aug 26, 2009 at 12:25 PM, Newson, Roger
> B<[email protected]> wrote:
>> This looks like possibly a job that should be done in 3 steps. First, use -statsby- in a loop to create an output dataset for each regression, with 1 observation, and variables containing the 2 coefficients, sample size, and R-squared. Second, use -append- in Stata 11, or the SSC package -dsconcat- in Stata 10 or lower, to concatenate these datasets into the memory, replacing the original dataset. Third, use -listtex-, downloadable from SSC, to produce the output LaTeX table, with header and/or footer rows, in a file, or in the Results window, to be cut and pasted into your LaTeX document.
>>
>> The -listtex- and -dsconcat- packages can be downloaded from SSC, using the -ssc- command in Stata. Both are cueenntly in Stata Version 10. Earlier versions can still be downloaded from my website by typing
>>
>> net from http://www.imperial.ac.uk/nhli/r.newson/
>>
>> and selecting the Stata version required.
>>
>> 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: [email protected]
>> 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.
>>
>> -----Original Message-----
>> From: [email protected] [mailto:[email protected]] On Behalf Of richard boylan
>> Sent: 26 August 2009 17:37
>> To: [email protected]
>> Subject: st: latex table with estimation results reported in rows and coefficient estimates listed in columns
>>
>> I was looking for a package to make latex table from regession
>> estimates except that I need the estimation results reported in rows
>> and coefficient estimates listed in columns.
>>
>> The only package that I could find that does that is est2tex, but when
>> one produces estimates in this horizontal format it suppresses the
>> r-squared and sample size.
>>
>> Does anyone know of any packages that allow this? I.e., I need
>>
>>
>> Coefficient 1 Coefficient 2 Sample
>> size R-squared
>> Reg 1
>>
>> Reg 2
>> *
>> * 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/
>
> *
> * 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/
