You are not currently logged in.
Access JSTOR through your library or other institution:
If You Use a Screen ReaderThis content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Estimating the Power of the Two-Sample Wilcoxon Test for Location Shift
Bruce Jay Collings and Martin A. Hamilton
Vol. 44, No. 3 (Sep., 1988), pp. 847-860
Published by: International Biometric Society
Stable URL: http://www.jstor.org/stable/2531596
Page Count: 14
You can always find the topics here!Topics: Estimation methods, Sample size, Simulations, Statistical variance, Statistical estimation, Statistics, Bootstrap resampling, Arithmetic mean, Power lines, Biometrics
Were these topics helpful?See somethings inaccurate? Let us know!
Select the topics that are inaccurate.
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Preview not available
Traditional methods for calculating the power of a statistical test for location shift require knowledge of the shape of the underlying probability distribution. The distribution shape, however, may be unknown. This paper describes a bootstrap method for using observed data (or pilot data) to approximate the power. No assumptions need be made about the shape of the underlying continuous probability distribution. Simulation evidence shows that, when applied to the Wilcoxon two-sample test for location shift, the suggested method is reliable. The evidence also shows that it is more accurate than a benchmark traditional approach. The bootstrap method is applied to a real-data example. The analysis demonstrates how the method can be used to determine sample sizes and how to choose the more powerful of two alternative tests for location shift.
Biometrics © 1988 International Biometric Society