Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature: OR to RR conversion in TSA #8

Open
lilleoel opened this issue Sep 5, 2022 · 0 comments
Open

Feature: OR to RR conversion in TSA #8

lilleoel opened this issue Sep 5, 2022 · 0 comments

Comments

@lilleoel
Copy link
Collaborator

lilleoel commented Sep 5, 2022

Hi,

My name is Tom Payne - I'm a researcher from Sydney, Australia, focussing mostly on meta-analysis. I'm a huge fan of the TSA software - thanks for the great ongoing work that you're doing!

I'm just emailing because of a query I have with the software. I note that when 'odds ratio' is selected as the measure of effect for the meta-analysis, when one then selects the 'based on trials at low risk of bias' option for the relative risk reduction (for calculation of the required information size) - the figure provided is actually a reflection of the odds ratio rather than the risk ratio. There is no conversion from the point estimate of the odds ratio into a risk ratio. For example, if the point estimate for the odds ratio meta-analysis was 0.7, when TSA software calculates the relative risk reduction, it gives the figure 30%; but this is the reduction in odds, not the reduction in risk. An odds ratio of 0.7, arbitrarily assuming a baseline prevalence of 40%, corresponds to a risk ratio of 0.8, and hence a RRR of 20%.

I was wondering if this was a mistake in the software or if I was missing something? Just thought I would reach out and check because as I said I'm a fan of the software and wouldn't want researchers to accidentally be getting the wrong relative risk reductions for their calculations.

Cheers,

Tom

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant