Re: st: R: Power Analysis

[Aggie Chidlow <mojamalarybka@googlemail.com>]

Dear Carlo,

Thank you very much for your response and suggestions. It is much appreciated.

Since posted to the list, I have done a chi2 test  to see if there is,
for example, a significant relationship between mentioning (or not)
the famework and the type of a journal.
After some thinking, I am planning to do a meta-analysis and would
appreciate if you (or anybody from the list) advise me how to do a
power analysis for the meta-analysis.

So sorry for any confusions, but I am at a finding the right tool stage.
Your suggestions will be much appreciated.


On Sun, Apr 4, 2010 at 12:06 PM, Carlo Lazzaro
<carlo.lazzaro@tiscalinet.it> wrote:
> Dear Agge,
> in the light of the details you provide the list with, unless you intend to
> perform a two-sample comparison of proportions (ie, how many articles
> deserved to be mentioned out of the overall number of articles submitted for
> possible publication in the sample #1 and #2, respectively), your problem
> seems more a matter of logistic regression  (please, see -help logit- in
> Stata 9.2/SE)than power analysis.
>
> However, should power analysis be the focus of your reserch, please take a
> look at -help sampsi- in Stata 9.2/SE.
>
> For more details about this issues, I would refer to:
> Long JS, Freese J. Regression Models for Categorical Dependent Variables
> Using Stata. 2nd Ed. College Station, TX: Stata Press, 2006;
>
> http://www.indiana.edu/~statmath/stat/all/power/index.html.
>
> HTH and Kind Regards,
> Carlo
> -----Messaggio originale-----
> Da: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] Per conto di Aggie Chidlow
> Inviato: sabato 3 aprile 2010 22.39
> A: statalist@hsphsun2.harvard.edu
> Oggetto: st: Power Analysis
>
> Hi,
>
> I am working on a paper where I am investigating if  researchers that
> published papers  between 2000 - 2008 with mail survey data in 4 top
> rated journals in economics report a certain framework (measured as 0
> = mentioned ; 1 = not mentioned).
>
> Can somebody advise me on how to undertake a power analysis for this,
> please?
> Many thanks in advance.
>
> Agge
>
> *
> *   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/