|
Activity Number:
|
316
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 5, 2008 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistical Education
|
| Abstract - #300729 |
|
Title:
|
Confidence Intervals for the Difference Between Two Means
|
|
Author(s):
|
Weiwen Miao*+
|
|
Companies:
|
Haverford College
|
|
Address:
|
370 Lancaster Ave, HAVERFORD, PA, 19041,
|
|
Keywords:
|
Behren-Fisher Problem ; Coverage probability ; Expected length ; preliminary test ; Shapiro-Wilk test ; Welch-Satterthwaite
|
|
Abstract:
|
The talk compares three confidence intervals for the difference between two means when the distributions are non-normal and their variances are unknown. The confidence intervals considered are Welch-Satterthwaite interval, the adaptive interval that incorporates a preliminary test (pre-test) of symmetry; and the adaptive interval that incorporates the Shapiro-Wilks test as a pre-test. The adaptive intervals use the Welch-Satterthwaite interval if the pre-test fails to reject symmetry (or normality) for both distributions; otherwise, apply the Welch-Satterthwaite interval to the log-transformed data, then transform the interval back. Our study shows that the adaptive interval with pre-test of symmetry has the best coverage among the three intervals considered.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2008 program |
