Hartung, JoachimMakambi, Kepher H.2004-12-062004-12-062000http://hdl.handle.net/2003/505810.17877/DE290R-13986The best linear unbiased estimator of the common mean in heteroscedastic one-way fixed effects model exists only if the values of the variance components are known. In practice this does not hold and so far there exists no consensus on the most suitable test for the common mean parameter. With respect to the attained significance levels, the tenUniversitätsbibliothek Dortmund310Alternative Test Procedures and Confidence Intervals on the Common Mean in the Fixed Effects Model for Meta-Analysisreport