|
Activity Number:
|
134
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #300827 |
|
Title:
|
A New Confidence Interval for a Simple Effect in a 2-by-2 Factorial Experiment Utilizing Uncertain Prior Information That the Two-Factor Interaction Is Zero
|
|
Author(s):
|
Paul Kabaila*+ and Khageswor Giri
|
|
Companies:
|
La Trobe University and La Trobe University
|
|
Address:
|
Department of Mathematics and Statistics,, Melbourne, International, 3086, Australia
|
|
Keywords:
|
confidence interval ; prior information ; 2-by-2 factorial experiment ; frequentist ; two-factor interaction
|
|
Abstract:
|
Consider a 2-by-2 factorial experiment with more than one replicate. Suppose that the parameter of interest theta is a specified simple effect and that we have uncertain prior information that the two-factor interaction is zero. We describe a new frequentist 1-alpha confidence interval for theta that utilizes this prior information. This interval has expected length that (a) is relatively small when the two-factor interaction is zero and (b) has maximum value that is not too large. This interval also has the following desirable properties. Its endpoints are continuous functions of the data and it coincides with the standard 1-alpha confidence interval when the data strongly contradicts the prior information.
|
