robumeta and within-study variance estimates for each effect size estimate

[Reza Kahlaee]

Hi

I am running a meta-regression on the effect of a specific drug on a group of people, I need to run meta-regression to find sources of heterogeneity, and I came across the Robust Variance Estimation and therefore need to run robumeta.

First I want to know how to calculate within-study variance estimates for each effect size estimate?

Does anybody know how to calculate within-study variance?

I would be happy for any help.

Kind regards

Reza

[Phil Bromiley]

You didn't get a quick answer. You'll increase your chances of a helpful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex.

Part of the problem is that this seems like a pretty specialized issue. Can you perhaps restate it in conventional statistical terms? Obviously, if the original data is in Stata, you can use margins to get effect sizes and variances. But, I'm not sure how you do this with meta analysis.