| From | Roger Newson <[email protected]> |
| To | [email protected] |
| Subject | Re: st: Displaying system variables after a meta-analysis using 'meta' |
| Date | Tue, 10 May 2005 14:41:02 +0100 |
At 14:01 10/05/2005, Roger Harbord wrote:
Another possible package for doing a meta-analysis is -metaparm-, downloadable from SSC using the -ssc- command. Whether you use -metan- or -metaparm- to do the calculations, you might like to use the -eclplot- package (also downloadable from SSC) to do the confidence interval plots, as -eclplot- is written in Stata 8, which contains better graphics than previous Stata versions.--On 09 May 2005 17:43 +0100 Andrea Mann <[email protected]> wrote:Dear Andrea,Dear all, I have performed a meta-analysis using the 'meta' command and would like to outfile the odds ratio, lower confidence limit, upper confidence limit and fixed and random weights, for each individual study, to a raw file. What are the names of the system variables for the odds ratio, lower ci, upper ci and the weights? I intend to generate variables from these system variables, collapse, and outfile. Is that correct?
It's probably going to be a little easier if you switch to use -metan- instead of -meta- as -metan- generates new variables containing the weights and CI limits. The most recent version of -metan- accepts the same input variables in the same order as -meta- i.e. effect estimates and standard errors. This is version 1.81 and is obtained by typing -ssc intall metaaggr, replace-. Full documentation including names of the variables left behind is available at <http://www.ihs.ox.ac.uk/csm/metan/metan_updates.pdf>
How you best handle the variables afterwards depends on what you want to use them for which you know better than us.
| © Copyright 1996–2024 StataCorp LLC | Terms of use | Privacy | Contact us | What's new | Site index |