|
|
|
|
|
.-
|
|
|
|
|
|
help for ^metainf^ (STB-47: sbe26; STB-56: sbe26.1)
|
|
|
|
|
|
.-
|
|
|
|
|
|
|
|
|
|
|
|
Influence of a single study in the meta-analysis estimates
|
|
|
|
|
|
----------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
^metainf^ theta setheta [^if^ exp] [^in^ range] [,^id(^labvar^)^ ^eform^ ^random^
|
|
|
|
|
|
^print^ graph_options]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Description
|
|
|
|
|
|
-----------
|
|
|
|
|
|
|
|
|
|
|
|
^metainf^ investigate the influence of a single study on the overall meta-
|
|
|
|
|
|
analysis estimate. This command shows graphically the results of an influence
|
|
|
|
|
|
analysis, in which the meta-analysis estimates are computed omitting one study
|
|
|
|
|
|
in each turn.
|
|
|
|
|
|
|
|
|
|
|
|
^theta^ is the effect estimated from the individual study, and ^setheta^ is its
|
|
|
|
|
|
standard error. For example theta might be a difference in means, a log rate
|
|
|
|
|
|
ratio, a log odds ratio, or a log hazard ratio.
|
|
|
|
|
|
|
|
|
|
|
|
If you have a dataset which contains data for all studies, then the @byvar@
|
|
|
|
|
|
command can be used to derive the effect estimates and standard errors for the
|
|
|
|
|
|
individual studies. For example:
|
|
|
|
|
|
|
|
|
|
|
|
. ^sort study^
|
|
|
|
|
|
. ^byvar study, coef(group) se(group) generate:^
|
|
|
|
|
|
. ^quietly poisson cases group, e(pyrs)^
|
|
|
|
|
|
. ^sort study^
|
|
|
|
|
|
. ^qui by study: keep if _n==1^
|
|
|
|
|
|
. ^rename _C_1 logrr^
|
|
|
|
|
|
. ^rename _S_1 logse^
|
|
|
|
|
|
. ^metainf logrr logse, id(study)^
|
|
|
|
|
|
|
|
|
|
|
|
Alternatively, the @collapse@ command may be useful.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Options
|
|
|
|
|
|
-------
|
|
|
|
|
|
|
|
|
|
|
|
^id(^labvar^)^ is a variable which is used to label the studies.
|
|
|
|
|
|
|
|
|
|
|
|
^eform^ requests that the output is exponentiated.
|
|
|
|
|
|
|
|
|
|
|
|
^random^ request random-effects estimates. By default fixed-effects estimates
|
|
|
|
|
|
are computed.
|
|
|
|
|
|
|
|
|
|
|
|
^print^ shows the estimates, and their 95% confidence interval, of the meta-
|
|
|
|
|
|
analysis estimates omitting one study in each turn. These values are used to
|
|
|
|
|
|
make the graphic.
|
|
|
|
|
|
|
|
|
|
|
|
All ^hplot^ options are also available.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Note
|
|
|
|
|
|
----
|
|
|
|
|
|
|
|
|
|
|
|
To run the ^metainf^ command, the ^meta^ [STB-43 sbe16.2, STB-42 sbe16.1,
|
|
|
|
|
|
STB-38 sbe16] and the ^hplot^ (Cox 1999a, 1999b) command must be installed.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Examples
|
|
|
|
|
|
--------
|
|
|
|
|
|
|
|
|
|
|
|
. ^metainf logrr logse, print id(studyid)^
|
|
|
|
|
|
. ^metainf logrr logse, random print id(studyid)^
|
|
|
|
|
|
. ^metainf logrr logse, random eform id(studyid) format(%4.2f)^
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
References
|
|
|
|
|
|
----------
|
|
|
|
|
|
|
|
|
|
|
|
Cox NJ (1999a). -hplot- and -hbar- for presentation graphics. Proceedings
|
|
|
|
|
|
of the 5th Stata UK user group meeting, London, UK.
|
|
|
|
|
|
|
|
|
|
|
|
Cox NJ (1999b). De tablas a gr<67>ficos, presentaciones en Stata. Proceedings
|
|
|
|
|
|
of the 1st Iberian user group meeting, Cordoba, Spain.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Author
|
|
|
|
|
|
------
|
|
|
|
|
|
|
|
|
|
|
|
Aurelio Tobias
|
|
|
|
|
|
Universidad Miguel Hernandez, Alicante, Spain
|
|
|
|
|
|
email: bledatobias@@ctv.es
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Also see
|
|
|
|
|
|
--------
|
|
|
|
|
|
|
|
|
|
|
|
On-line: help for @byvar@, @collapse@, @for@, @meta@ (if installed), @metareg@ (if
|
|
|
|
|
|
installed), @metabias@ (if installed), @metacum@ (if installed), @galbr@
|
|
|
|
|
|
(if installed), metap (if installed), @hplot@ (if installed)
|
|
|
|
|
|
|
