SINGLE SAMPLE COMMERCIAL TESTING

SEVERAL METHODS HAVE BEEN USED FOR TESTING ALTERNATIVE TV COMMERCIALS. TYPICALLY, INDEPENDENT SAMPLES OF RESPONDENTS ARE EXPOSED TO THE TEST COMMERCIALS. A MODEL BY WILLIAMS (1950) ADJUSTS THE MEANS FOR BOTH FIRST AND SECOND RESIDUAL EFFECTS. THIS IS THE DESIGN PROPOSED FOR TESTING THREE TV COMMERCI...

Full description

Saved in:
Bibliographic Details
Published in:Journal of advertising research 1973-12, Vol.13 (6), p.39-42
Main Author: Plasman, Stephen K
Format: Article
Language:English
Subjects:
Commercials
Television advertising
Test methods
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:SEVERAL METHODS HAVE BEEN USED FOR TESTING ALTERNATIVE TV COMMERCIALS. TYPICALLY, INDEPENDENT SAMPLES OF RESPONDENTS ARE EXPOSED TO THE TEST COMMERCIALS. A MODEL BY WILLIAMS (1950) ADJUSTS THE MEANS FOR BOTH FIRST AND SECOND RESIDUAL EFFECTS. THIS IS THE DESIGN PROPOSED FOR TESTING THREE TV COMMERCIALS. IN IT, TWO 3 X 3 LATIN SQUARES ARE USED. EACH TREATMENT IS PRECEDED BY EACH PAIR OF OTHER TREATMENTS SO THAT THE DESIGNS ARE BALANCED FOR THE EFFECTS OF PAIRS OF RESIDUAL EFFECTS. THIS DESIGN MAKES IT FEASIBLE TO USE THE SAME RESPONDENTS SO THAT THE MATCHING OF SAMPLES IS NOT REQUIRED AND THE STATISTICAL ADJUSTMENT CAN BE EFFECTIVELY MADE TO TREATMENT MEANS RECOGNIZING BOTH FIRST RESIDUAL EFFECTS AND SECOND RESIDUAL EFFECTS WHEN TESTING. IN ORDER TO TEST THE MODEL, THREE COMMERCIALS FOR A PARTICULAR BRAND OF CEREAL AND THREE COMMERCIALS FOR A FINANCIAL INSTITUTION WERE TESTED.
ISSN:0021-8499
1740-1909