One possibility for automating this kind of job is to use the -parmest-
package to produce datasets of odds ratios and to use the -eclplot-
package to produce the plots of confidence intervals. Both the -parmest-
package and the -eclplot- package can be downloaded from SSC, using the
-ssc- command. The -parmest- package contains a module -parmby-, which
can produce a dataset containing odds ratios for several by-groups, and
a module -metaparm-, which can calculate weighted geometric mean odds
ratios. The on-line help for -parmest- and -eclplot- contains references
to various presentations and other documents describing the use of
-parmest- and -eclplot-.
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: www.imperial.ac.uk/nhli/r.newson/
Departmental Web page:
http://www1.imperial.ac.uk/medicine/about/divisions/nhli/respiration/pop
genetics/reph/
Opinions expressed are those of the author, not of the institution.
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Anthony
Staines
Sent: 28 September 2008 19:59
To: [email protected]
Cc: carla perrotta
Subject: st: Graphing of multiple meta-analyses
Dear all,
I would be grateful for advice on the following question. We are doing a
pooled analysis of a number of case-control studies, mainly looking at
occupational exposures. We have a number of pre-specified analyses, but
we would also like to prepare and graph pooled estimates for about 80
occupational groups. (We are fully aware of the statistical and
inferential issues here.)
At the moment we are running the analyses, (using the metan command) and
manually transferring the individual and pooled OR, study sizes etc..
into a graphical command, to prepare a meta-analysis plot for each one.
We want to do two things - first eliminate this manual transfer step, as
it is error prone. Second prepare graphs containing several of these in
one graph.
I'm not a Stata expert, Carla, who is working on this project knows
Stata better than I do, but we would both be grateful for any
suggestions, hints, or plain instructions,
Best wishes,
Anthony Staines
--
Anthony Staines, Professor of Health Systems Research,
School of Nursing, Dublin City University, Dublin 9,Ireland.
Tel:- +353 1 700 7807. Mobile:- +353 86 606 9713
*
* 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/
