Advances and Applications in Statistics
Volume 43, Issue 1, Pages 1 - 20
(November 2014)
|
|
AN ADAPTATION OF LAN METHOD FOR MONITORING CUMULATIVE CORRELATIONS
Samson Henry Dogo
|
Abstract: Cumulative meta-analysis (CMA) is used to indicate statistical sufficiency in accumulating evidence and to stop clinical trials as early as possible. But by definition the technique involves multiple looks on the accumulating evidence which inflates the Type I error in the analysis. This paper formulates a Hu et al. [10, 14] test to control the Type I error and to monitor cumulative meta-analysis of correlation. Simulations show that the test based on the r metric is more powerful compared to the test based on the z metric in FEM and the revise is the case in REM. Applications of the test are illustrated using a meta-analysis from ecology. |
Keywords and phrases: correlation, cumulative meta-analysis, fixed effect model, random-effects model. |
|
Number of Downloads: 345 | Number of Views: 1053 |
|