Stata 17 - how to get forest plots with risk ratio and not log risk ratio

[Ind Aus]

Hi
I am new to Stata 17 meta analysis forest plots.
I am analysing binary data for treatment(Yes/No) and Control (Yes/No).
I use dropdown list in Stata --> Statistics --> meta analysis --> setup --> binary data ---> entered variables with and without outcomes for treatment and control --> log risk ratio --> random effects.--> summary --> forest plot
The forest plot has log Risk ratio and not Risk ratio.
Please advise how I could have the output as Risk ratios in the forest plot (not log risk ratio).
Thanks in advance.

[Ind Aus]

Please ignore my request.
I just found out how to do it

[Andrew Musau]

Good that you solved your problem, but please note that Statalist is not a helpline. It is possible that others will have the same question in the future and will benefit from your solution. Therefore, you should post your solution. This is indicated in FAQ Advice #16.

16. How should I maintain threads I start?

16.1 Close by giving a summary and thanks


Trying to wrap up a thread you started is helpful, especially if you report what solved your problem.

[Ind Aus]

Hi Andrew

Thanks.

The following resolved the issue.

. meta forestplot, transform(`"Risk ratio"': invlogit)

Please close the thread.

[Andrew Musau]

Thanks for posting the solution.

Please close the thread.

Your response does so, but someone else with a related problem may reopen the thread at some point in the future.

[Leonardo Guizzetti]

Hi Andrew

Thanks.

The following resolved the issue.

. meta forestplot, transform(`"Risk ratio"': invlogit)

Please close the thread.

Actually, this did not solve your problem, assuming you actually specified a meta-analysis on the log-risk ratio scale. See the example for how to back-transform to a risk ratio.

webuse bcg
meta esize npost nnegt nposc nnegc, esize(lnrratio)
meta summarize
meta summarize, rr