Reducing the Number of Unjustified Significant Results in Meta-analysis

A normal distribution reference to the standard test for the overall treatment efficacy in a one-way random effects ANOVA model and meta-analysis leads to unacceptable liberality. Using a convenient heterogeneity variance estimator, a test procedure (a confidence interval) is proposed and shown to a...

Full description

Saved in:
Bibliographic Details
Published inCommunications in statistics. Simulation and computation Vol. 32; no. 4; pp. 1179 - 1190
Main Authors Hartung, Joachim, Makambi, Kepher H.
Format Journal Article
LanguageEnglish
Published Colchester Taylor & Francis Group 11.01.2003
Taylor & Francis
Subjects
Applications
Confidence interval
Exact sciences and technology
Heterogeneity variance
Inference from stochastic processes; time series analysis
Mathematics
Medical sciences
Nonparametric inference
Overall treatment effect
Parametric inference
Probability and statistics
Random effects model
Risk difference
Sciences and techniques of general use
Statistics
Type I error probability
Statistical analysis
Heterogeneity variance
Error rate
Binary data
Variance analysis
Error type I
Confidence interval
Metaanalysis
Overall treatment effect
Risk difference
Random effect
Clinical trial
Medical application
Online AccessGet full text

Cover

More Information
Summary:A normal distribution reference to the standard test for the overall treatment efficacy in a one-way random effects ANOVA model and meta-analysis leads to unacceptable liberality. Using a convenient heterogeneity variance estimator, a test procedure (a confidence interval) is proposed and shown to attain type I error rates (confidence coefficients) which are closer to the nominal level compared with the standard procedure. The proposed test is also shown to perform well for data from binary experiments.
ISSN:0361-0918
1532-4141
DOI:10.1081/SAC-120023884