A Field Experiment Comparing Anchored and Unanchored Criteria Weights in the Analytic Hierarchy Process
✍ Scribed by CYNTHIA F. HADLEY; BERTRAM SCHONER; WILLIAM C. WEDLEY
- Publisher
- John Wiley and Sons
- Year
- 1997
- Tongue
- English
- Weight
- 203 KB
- Volume
- 6
- Category
- Article
- ISSN
- 1057-9214
No coin nor oath required. For personal study only.
✦ Synopsis
This study reports the results of a field experiment comparing the predictive validity of two approaches to multicriteria assessments: the absolute measurement mode of AHP and the absolute measurement mode of linking pin AHP. The questioning procedures of the two differ only in that the former employs unanchored criteria weight assessments and the latter anchored criteria weight assessments.
The decision task required insurance agents to respond to a mailed questionnaire in which they evaluated nonmonetary incentives (contests) according to (1) the public recognition received from winning, (2) the criteria for winning and (3) the nature of the reward. There were four levels for each dimension. A between subjects design was used, with each subject receiving one of the two methods. In addition, all subjects divided 100 points among four contests and these hold-out assignments were employed as a validity check. Linking pin AHP was found to be superior to conventional AHP in this experiment, lending weight to the argument that the use of unanchored criteria weights is problematic.