metafor (version 1.9-2)

dat.collins1985a: Studies on the Treatment of Upper Gastrointestinal Bleeding by a Histamine H2 Antagonist

Description

Results from studies examining the presence of persistent or recurrent bleedings in patients receiving either a histamine H2 antagonist or placebo.

Usage

dat.collins1985a

format

The data frame contains the following columns: lll{ id numeric study number ref numeric reference number year numeric year of publication nti numeric number of patients in treatment group xti numeric number of patients in treatment group with persistent or recurrent bleedings nci numeric number of patients in placebo group xci numeric number of patients in placebo group with persistent or recurrent bleedings }

source

van Houwelingen, H. C., Zwinderman, K. H., & Stijnen, T. (1993). A bivariate approach to meta-analysis. Statistics in Medicine, 12, 2273--2284.

Details

The data in this dataset were obtained from Table I in van Houwelingen, Zwinderman, and Stijnen (1993).

References

Collins, R., & Langman, M. (1985). Treatment with histamine H2 antagonists in acute upper gastrointestinal hemorrhage. New England Journal of Medicine, 313, 660--666.

Examples

### load data
data(dat.collins1985a)

### calculate (log) odds ratio and sampling variance
dat <- escalc(measure="OR", ai=xci, n1i=nci, ci=xti, n2i=nti,
              data=dat.collins1985a, to="all")
summary(dat, digits=2, transf=exp)

### meta-analysis of log odds ratios using Peto's method
res <- rma.peto(ai=xci, n1i=nci, ci=xti, n2i=nti, data=dat.collins1985a)
summary(res)

### meta-analysis of log odds ratios using conditional logistic regression model
res <- rma.glmm(measure="OR", ai=xci, n1i=nci, ci=xti, n2i=nti,
                data=dat.collins1985a, model="CM.EL", method="FE")
summary(res)

### plot the log-likelihoods of the odds ratios
llplot(measure="OR", ai=xci, n1i=nci, ci=xti, n2i=nti, data=dat.collins1985a,
       lwd=1, refline=NA, xlim=c(-4,4), drop00=FALSE)

### meta-analysis of log odds ratios using conditional logistic regression model
res <- rma.glmm(measure="OR", ai=xci, n1i=nci, ci=xti, n2i=nti,
                data=dat.collins1985a, model="CM.EL", method="ML")
summary(res)