What question did this study set out to answer?

This research aims to compare the power of different statistical procedures in two-stage designs, assessing their efficiency and error rates.

Internal pilot studies II: comparison of various procedures

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial compares power of various statistical tests in clinical designs, highlighting efficiency and error control.

This research aims to compare the power of different statistical procedures in two-stage designs, assessing their efficiency and error rates.
Compared Stein's original test, idealized Wittes-Brittain test, and an approximate-optimal test.
Evaluated Gould and Shih's procedure alongside a newly proposed second segment procedure.
Analyzed power differences under varying conditions and sample sizes.
Stein's test was the preferred method under the original design alternative despite expectations.
Wittes-Brittain and approximate-optimal procedures showed superior power for detecting smaller treatment differences.
The second segment procedure outperformed Gould-Shih when many observations were taken after sample resizing.

Zucker et al. (1999) studied this question.

View Full Paper

Ask AI

Bookmark