meta: Results of 22 Clinical Trials of beta-Blockers
In BayesDA: Functions and Datasets for the book "Bayesian Data Analysis"

Description Usage Format Details Examples

Results of 22 clinical trials of beta-blockers for reducing mortality after myocardial infection. Used for meta-analysis.

1	data(meta)

A data frame with 22 observations on the following 5 variables.

study: id code of study
control.deaths: number of deaths in control group
control.total: total number of patients in control group
treated.deaths: number of deaths in treatment group
treated.total: total number of patients in treatment group

The 22 clinical trials each consist of two groups of heart attack patients randomly allocated to receive or not receive beta-blockers ( a family of drugs that affect the central nervous system and can relax the heart musckles).

data(meta)
names(meta)
# Calculating empirical log-odds and its sampling variances:
y <- apply(meta, 1, function(x) log( (x[4]/(x[5]-x[4]))/(x[2]/(x[3]-x[2])) ) )
s2 <- apply(meta, 1, function(x) 1/(x[5]-x[4]) + 1/x[4] +1/(x[3]-x[2]) + 1/x[2] )  
cbind("Study number"=meta[,1], "empirical log odds"=y, "empirical sampling variance of y"=s2)
#if(require(meta)){
#   funnel(y, sqrt(s2))
#   radial(y, sqrt(s2))
#}