|
Activity Number:
|
570
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 6, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Business and Economic Statistics Section
|
| Abstract - #304856 |
|
Title:
|
Testing the Equivalence of Means from a Multivariate Normal Population and Its Application to Investment
|
|
Author(s):
|
Hubert J. Chen*+ and Yen-Chi Huang and Minglong A. Wang
|
|
Companies:
|
National Cheng-Kung University and National Cheng-Kung University and National Cheng-Kung University
|
|
Address:
|
1 University Road, Tainan, 70101, Taiwan
|
|
Keywords:
|
Equivalence ; Distance statistic ; Least favorable configuration ; Level of a test ; Power function
|
|
Abstract:
|
Assuming a multivariate normal distribution, some distance test statistics are proposed to test the hypothesis of equivalence of means, where the equivalence is defined to be the maximum distance of treatment means from the grand mean being falling into a small but negligible zone. Some least favorable mean configurations (LFMCs) to guarantee the maximum level (type I error probability at a null hypothesis) and to guarantee the minimum power (the probability of a correct decision at an alternative hypothesis) are investigated. It is found that, at some LFMCs, the level and the power of the test are fully independent of the unknown means and variances. For a given null and a given alternative hypothesis, the p-value of the test and its power can be determined. A numerical example for investing in stock mutual funds is demonstrated.
|
