A Comparison of the Analytic Hierarchy Process and the Geometric Mean Procedure for Ratio Scaling
Interim rept. Mar 1984-Mar 1985
NORTH CAROLINA UNIV AT CHAPEL HILL PSYCHOMETRIC LAB
Pagination or Media Count:
This research note evaluates and compares the performance of two methods of ratio scaling the analytic hierarchy process proposed by Saaty 1977, 1980, and the geometric mean procedure advocated by Williams and Crawford 1980 when random data are supplied. The two methods are examined in a series of Monte Carlo simulations for two response methods direct estimation and constant sum and for various stimuli and response scales. The sampling distributions of the measures of consistency of two methods are tabulated, rules for detecting and rejecting inconsistent respondents are outlined, and approximation formulas for other designs are derived. Overall, there is a high level of agreement and correspondence between the results from the two scaling techniques. We conclude that the present results reinforce Williams and Crawfords claim for the superiority of the geometric mean procedure. Keywords Psychometrics.
- Statistics and Probability