st: metan v9 update

[RJ Harris <ross.harris@bristol.ac.uk>]

Dear Stata users

Thanks to Kit Baum, an updated version of the meta-analysis package -metan- 
is now available from the SSC archive.

In addition to providing a comprehensive range of options for meta-analysis 
of 2x2 tables and of mean differences, these routines provide methods for 
the meta-analysis of summary (aggregate) data (for example the log odds 
ratio and its standard error) from each study. Tests of the null hypothesis 
that the summary treatment effect is null are reported, as well as a test 
for heterogeneity (whether the true effect in all studies is the same). 
Heterogeneity is also quantified using the I-squared statistic (Higgins et 
al 2003).

The original code for -metan- was written by Mike Bradburn, Jon Deeks and 
Doug Altman. Those of you familiar with the original -metan- command as 
updated over the years will find everything works much as it used to. As 
before, the results may be displayed graphically in a forest plot, and the 
-by- option may be used to produce and display results in subgroups. 
However, the graph routines have now been completely re-written and several 
new features added:

�	Version 9 graphics: it is possible to use Stata 9 graphics options to 
change all aspects of the forest plot
�	Flexible, tabular display with the option to display addition columns of 
data on either side of the forest plot
�	Summary results from meta-analyses using two different methods may be 
displayed together in the forest plot. Alternatively, summary estimates may 
be suppressed.
�	The predictive distribution of random effects analyses may be displayed 
as an extended confidence interval as described by Higgins and Thompson 
(2006)

All of these features (and more) are explained in the help file, which 
contains several clickable examples showing the use of the new command.

To install -metan-, please type:

-ssc install metan-

and to view the help file

-help metan-

Comments and suggestions are welcome, and should be sent to 
ross.harris@bristol.ac.uk.

We are grateful to Patrick Royston (MRC Clinical Trials Unit, London UK) 
and to Vince Wiggins and Jeff Pitblado (StataCorp) for extensive advice and 
suggestions. We hope that the new features are useful.

Best wishes,

Ross Harris, Roger Harbord and Jonathan Sterne
Department of Social Medicine, University of Bristol UK
www.epi.bris.ac.uk


References

Higgins JPT, Thompson SG, Deeks JJ, Altman DG.  Measuring inconsistency in 
meta-analyses.  BMJ 2003; 327:557-560. 
http://dxi.org/10.1136/bmj.327.7414.557

Higgins JPT, Thompson SG (2006) Presenting random effects meta-analyses: 
where we are going wrong? (from presentation, work in preparation)


----------------------
Ross Harris
Department of Social Medicine
University of Bristol
+44 (0)117 928 7338
Ross.Harris@bristol.ac.uk

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/