A discrete probabilistic model for analyzing pairwise comparison matrices

Abstract

The pairwise comparison matrix is often used for the estimation of the priorities in the analytic hierarchy process. In this paper, we propose an estimation method based on the discrete probabilistic expression of each choice. Moreover, we show numerical examples to compare our method with commonly used ones. As a result, it is shown that, using a robust divergence measure for the estimation, the proposed method can extract the priorities more stably even if some outlying observations are included.

Keywords:

• BHHJ divergence
• decision analysis
• multiple-criteria analytic hierarchy process
• pairwise comparison matrix
• robustness

Acknowledgement

The authors would like to express gratitude to the reviewer and the editor-in-chief for their valuable comments, which remarkably improved our earlier draft.

Additional information

Funding

This work was partly supported by JSPS KAKENHI Grant Number 16J04579.