|
Activity Number:
|
514
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 7, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistical Computing
|
| Abstract - #301545 |
|
Title:
|
Sample Size Estimation Tables for Effect Size Values for the Significant Interaction Effect of a Completely Randomized Factorial Design (CRF-pq): Fixed Effects and Random Effects
|
|
Author(s):
|
Larry W. Featherston*+ and Calli Johnson and Charles Stegman and Denise T. Airola
|
|
Companies:
|
University of Arkansas and University of Arkansas and University of Arkansas and University of Arkansas
|
|
Address:
|
NORMES, 346 West Avenue, Fayetteville, AR, 72701,
|
|
Keywords:
|
Power ; Effect Size ; Sample size ; CRF-pq ; Completely Randomized Factorial Designs ; Randomized Block Designs
|
|
Abstract:
|
The purpose of this paper is to extend the work of Kirk (1995) and Foster's (1993) on estimating sample sizes for effect size values of Completely Randomized and Randomized Block designs. While Foster's sample size estimation tables are an invaluable resource for researchers using simple research designs, no such resource exist for researchers who are using more complex research designs. Therefore, this paper provides an explanation of the calculations and sample size estimation tables for the signification interaction effects of a Completely Randomized Factorial (CRF-pq) designs for both Fixed and Random Effects Models. Sample size estimation tables have been completed for CRF-22 through CRF-35 designs.
|
