Authors: | Hartung, Joachim Makambi, K. H. |
Title: | Simple t-distribution Based Tests for Meta-Analysis |
Language (ISO): | en |
Abstract: | The variance function of the optimal estimator of the overall mean in a heteroscedastic one-way ANOVA model is dominated by positive semi-definite quadratic functions. This makes it possible to develop closely related tests on the nullity of the overall mean parameter, in one-way fifixed and random effects ANOVA models, which make use of the quantiles of the t-distribution. These tests are founded on the convexity arguments similar to Hartung (1976). Simulation results indicate that the proposed tests attain type I error rates which are far more acceptable than those of the commonly used tests. |
Subject Headings: | balanced and unbalanced samples estimated degrees of freedom fixed and random effects models homoscedastic and heteroscedastic error variances replication type I error rate |
URI: | http://hdl.handle.net/2003/4925 http://dx.doi.org/10.17877/DE290R-5425 |
Issue Date: | 1999 |
Provenance: | Universitätsbibliothek Dortmund |
Appears in Collections: | Sonderforschungsbereich (SFB) 475 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
99_38.pdf | DNB | 162.34 kB | Adobe PDF | View/Open |
tr38-99.ps | 123.08 kB | Postscript | View/Open |
This item is protected by original copyright |
This item is protected by original copyright rightsstatements.org