Sec.2-Ch.1-Subsec.6：Meta-Analysis of Continuous Variables in R
From Theory to Practice with Visualization and Sensitivity Analysis
Meta-analysis is a method for synthesizing results from multiple studies and is commonly used to evaluate the overall effect of an intervention or treatment. In many scientific studies, meta-analysis helps assess the robustness and generalizability of experimental data. Especially in the fields of medicine and psychology, meta-analysis can effectively integrate heterogeneity across studies, improving statistical power and the accuracy of results.
This article focuses on meta-analysis of continuous variables, particularly using the meta extension package in R. The analysis is demonstrated using the Fleiss93cont dataset.
I. The Fleiss93cont Dataset
The Fleiss93cont dataset in the R meta extension package originates from a meta-analysis published by E. Mumford et al. (1984) on the impact of mental health treatment on medical service utilization. The dataset contains basic information from five studies, including study year, sample sizes, means, and standard deviations for both treatment and control groups.
library(meta)
data(Fleiss93cont)
Fleiss93contThe contents of the Fleiss93cont dataset are as follows:
study year n.e mean.e sd.e n.c mean.c sd.c
1 Davis 1973 13 5.0 4.70 13 6.50 3.80
2 Florell 1971 30 4.9 1.71 50 6.10 2.30
3 Gruen 1975 35 22.5 3.44 35 24.90 10.65
4 Hart 1975 20 12.5 1.47 20 12.30 1.66
5 Wilson 1977 8 6.5 0.76 8 7.38 1.41study: study label
year: year of the study
n.e: total number of participants in the treatment group
mean.e: mean outcome in the treatment group
sd.e: standard deviation in the treatment group
n.c: total number of participants in the control group
mean.c: mean outcome in the control group
sd.c: standard deviation in the control group
The dataset contains 5 studies, primarily used to analyze the impact of mental health treatment on medical service utilization.
