st: RE: AW: RE: RE: Estout for metan?

[Megan Fesinmeyer <mfesinme@WHI.org>]

This is a wonderful, simple solution, and seems that it should work for my analyses.  Except, when I run the -statsby- command, although all the meta-analyses appear to run (and all 187 forest plots flash by on my screen), the resulting dataset is empty.  There's a variable for each of the scalars stored in (r), but all of the values are missing. Any ideas what I'm doing wrong?

Thanks again,
Megan

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Martin Weiss
Sent: Thursday, August 05, 2010 8:49 AM
To: statalist@hsphsun2.harvard.edu
Subject: st: AW: RE: RE: Estout for metan?


<> 

Re -statsby-, also see NJC`s recent
http://www.stata-journal.com/article.html?article=gr0045




HTH
Martin


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Roger Harbord
Gesendet: Donnerstag, 5. August 2010 17:43
An: statalist@hsphsun2.harvard.edu
Betreff: st: RE: RE: Estout for metan?

An alternative solution should be possible using -statsby-. You'd need
to first append all your study data into a single large file and
create an extra ID number to indicate which meta-analysis each study
belongs to (you could probably do that with a single very long command
of the form -append using file1 file2...file200, generate(metaid)- ).
You should then be able to use -statsby- to automatically loop over
the meta-analyses and collect the  various results you want that
-metan- returns in r().

Roger.
--
Roger Harbord
http://www.epi.bris.ac.uk/staff/rharbord.htm

On 30 July 2010 17:06, Megan Fesinmeyer <mfesinme@whi.org> wrote:
> Thank you so much for this idea!  I will give it a try.  I had sort of
given up yesterday, and spent the day reformatting my data to perform
meta-analysis in METAL software.  I'd much rather use Stata, so it would be
great if I can get this approach to work.
>
>
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Tiago V. Pereira
> Sent: Thursday, July 29, 2010 1:14 PM
> To: statalist@hsphsun2.harvard.edu
> Subject: st: RE: Estout for metan?,
>
> Megan,
>
> A very straightforward solution is to create a folder with all your
> meta-analyses numbered from 1 to 200, say, meta_analysis_1.dta,
> meta_analysis_2.dta, and so on. Then, loop over them storing the results
> as locals. Finally, create a single file will all results and use
> -outsheet- to get a xls file (tab-delimited by default).
>
>
> An very simple example is presented below.
>
>
> All you need to modify is the path to find your files. If you use windows
> the paths are like
>
> "C:\myfiles\meta_analysis_`i'.dta"
>
> Hope this helps.
>
> Copy-paste tasks are really prone to errors! Let me know if this simple
> code works for you. I did not check its accuracy.
>
> Tiago
>
>

*
*   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/