[R] Mantel-Haenszel relative risk with Greenland-Robins variance estimate

[Thomas Lumley]

On Tue, 8 May 2007, Frank E Harrell Jr wrote:

> Does anyone know of an R function for computing the Greenland-Robins
> variance for Mantel-Haenszel relative risks?

Both the (almost identical) meta-analysis packages compute the MH 
estimator for relative risks and its standard error.

 	-thomas

Thomas Lumley			Assoc. Professor, Biostatistics
tlumley at u.washington.edu	University of Washington, Seattle