Meta-Analysis Resources

Tools for Those Who Summarize the Evidence Base

Resources and networking for those who conduct or interpret meta-analyses related to any phenomenon that is gauged in multiple studies.

Meta-regression question

As I mentioned in the 'methodological quality' forum, I am currently working on a risk association meta-analysis involving case-control studies. 

Not surprisingly, our meta-analysis has a substantial heterogeneity of I-squared of 90%. We are trying to do a metaregression and subgroup analysis which might explain some of the heterogeneity. 

The question I have is how do we form a regression equation in the form of y = a+bx? Is Y here the 90% heterogeneity? And the regression variable (b1, b2, b3, etc) the covariates that I will be using for the metaregression? 

Also, how does one do a metaregression in STATA? I am currently using comprehensive meta-analysis and it is working well, but I would like to learn to use the metareg command in STATA. 

Thanks so much. 

Views: 163

Replies to This Discussion

Permalink Reply by Blair T. Johnson on April 9, 2014 at 11:09pm

You might like to view a video I posted recently on YouTube that explains how to use meta-regression in Stata, available here. It also shows how to move the constant to estimate the mean effect size (and the confidence interval) at particular values of your moderator.

Permalink Reply by Yeshvanth JP on April 12, 2014 at 11:26am

Thank you, Dr. Johnson. This was very helpful. 

RSS

© 2021   Created by Blair T. Johnson.   Powered by

Badges  |  Report an Issue  |  Terms of Service