2
$\begingroup$

I have done a meta analysis and heterogeneity is too high. I am working with (even/Total) for experimental and control groups to calculate the Odds Ratio. I have done fixed-effect and random-effect modeling. I now need to use meta-regression via SPSS.

Can anyone direct me to a good set of materials to learn how to do this? I have read some links but none has really solved this question. Thanks

$\endgroup$
3
  • $\begingroup$ I am also trying to do fixed-effect and random-effect modeling ( panel data) using SPSS. Can anybody tell me how to do it in SPSS. Thank you for you help. $\endgroup$
    – user4285
    Commented Apr 22, 2011 at 1:22
  • $\begingroup$ Welcome to this site, @G! Please take a moment to read over the FAQ and acquaint yourself with the conventions here. In particular, because replies are treated so much differently than comments, we are careful to distinguish them. Your "I have this question too" is a useful comment but is not a helpful reply: that's why I have turned it into a comment. $\endgroup$
    – whuber
    Commented Apr 22, 2011 at 1:51
  • $\begingroup$ An anonymous user (who likely does not have the rep to create comments) has suggested www.metcardio.org as "a very interesting website." It appears legitimate, but is heavily focused on medical applications. $\endgroup$
    – whuber
    Commented Oct 17, 2011 at 20:30

1 Answer 1

7
$\begingroup$

You could start with David B Wilson's website on "meta-analysis stuff". He offers spss, stata, and sas macros for performing meta-analytic analyses (including meta-regression; metareg.sps) + PPT slides (analysis.ppt, interpretation.ppt).

Another presentation I really like(d) was given by Marsh et al. „Meta-Analysis: Session 3.3 & 3.4: Teacher Expectancy Example” (see "Practical example - fixed, random, & multilevel Meta20 data"). Unfortunately, the presentation seems to be no longer available... But you might want to check the other resources (see esp. "Advanced Meta-Anaylsis Seminar Presentations").

Finally, you can find a presentation on "Random and Mixed-effects Modeling" on the website of the Campbell Collaboration.

$\endgroup$
1
  • 1
    $\begingroup$ Wilson's macros are definitely the way to go if you want to use SPSS. You may also consider picking up a copy of "Practical Meta-Analysis" by Lipsey & Wilson. $\endgroup$
    – Wolfgang
    Commented Dec 8, 2010 at 12:37

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.