The Analysis of Subjective Judgment Matrices

by Gordon Crawford, Cindy Williams

Full Document

FormatFile SizeNotes
PDF file 1.7 MB

Use Adobe Acrobat Reader version 10 or higher for the best experience.

A popular method for quantifying subjective judgment utilizes the dominant eigenvector of a matrix of paired comparisons. The eigenvector yields a scale of the importance of each element of a collection relative to the others. The scale is based on a matrix of subjective paired comparisons. Thomas Saaty has shown this to be a useful tool for analyzing hierarchical structures in many military and industrial applications: by estimating the scale at each level of a structured problem, this procedure yields the relative importance of the elements at the bottom level of the hierarchy to the goals or output at the top level. The geometric mean vector is computationally easier than and statistically preferable to the eigenvector. Further, the geometric mean vector is applicable to a wider class of problems and has the advantage of arising from common statistical and mathematical models. The statistical advantages are theoretically and empirically demonstrated.

This report is part of the RAND Corporation Report series. The report was a product of the RAND Corporation from 1948 to 1993 that represented the principal publication documenting and transmitting RAND's major research findings and final research.

Permission is given to duplicate this electronic document for personal use only, as long as it is unaltered and complete. Copies may not be duplicated for commercial purposes. Unauthorized posting of RAND PDFs to a non-RAND Web site is prohibited. RAND PDFs are protected under copyright law. For information on reprint and linking permissions, please visit the RAND Permissions page.

The RAND Corporation is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.