It's implemented in the metafor package.
Using the example from the pdf that Marc pointed out:
########################################################
library(metafor)
ai <- c(53, 121, 95, 103, 64, 7, 0)
bi <- c(2, 3, 14, 27, 51, 29, 13)
ci <- c(61, 152, 114, 66, 81, 28, 0)
di <- c(1, 5, 7, 12, 40, 101, 64)
res <- rma.mh(ai=ai, bi=bi, ci=ci, di=di)
res
res$BD
res$BDp
########################################################
yields exactly the same results:
res
Fixed-Effects Model (k = 7)
Test for Heterogeneity:
Q(df = 6) = 3.2892, p-val = 0.7718
Model Results (log scale):
estimate se zval pval ci.lb ci.ub
-0.4238 0.1763 -2.4039 0.0162 -0.7694 -0.0783
Model Results (OR scale):
estimate ci.lb ci.ub
0.6545 0.4633 0.9247
Cochran-Mantel-Haenszel Test: CMH = 5.4350, df = 1, p-val = 0.0197
Tarone's Test for Heterogeneity: X^2 = 2.3727, df = 5, p-val = 0.7955
res$BD
[1] 2.373063
res$BDp
[1] 0.7954786
Best,
--
Wolfgang Viechtbauer
Department of Psychiatry and Neuropsychology
School for Mental Health and Neuroscience
Maastricht University, P.O. Box 616
6200 MD Maastricht, The Netherlands
Web: http://www.wvbauer.com
----Original Message----
From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On
Behalf Of Marc Schwartz Sent: Tuesday, November 16, 2010 16:50
To: David Winsemius
Cc: R Help
Subject: Re: [R] Breslow-Day test
On Nov 16, 2010, at 9:18 AM, David Winsemius wrote:
On Nov 16, 2010, at 10:08 AM, Robert Ruser wrote:
Dear R Users,
I'm looking for a package that allows to test hypothesis about a
homogeneity of odds ratio in k 2x2 tables. I know that Breslow-Day is
suitable but does anybody could me point out a package? I found
diffR, but as far as I see this package is for IRT theory.
You might also want to look at:
http://statweb.calpoly.edu/aschaffn/418/documents/Script8.01.pdf
which has code that includes the Tarone adjustment based upon:
On Heterogeneity Tests Based on Efficient Scores
Tarone RE
Biometrika 72, 91-95. 1985
Supported by Breslow in:
Statistics in Epidemiology: The Case-Control Study
N. E. Breslow
Journal of the American Statistical Association
Vol. 91, No. 433 (Mar., 1996), pp. 14-28
and also look at the code for the woolf() function in ?mantelhaen.test
HTH,
Marc Schwartz