ANALYSIS OF THE RELIABILITY OF PREFERENCE RANKING DATA

The objective of this article is to investigate the reliability of stated preference ranking data. Theoretical developments of explicit treatment of uncertain reliability of ranking data are presented followed by an empirical analysis of a preference ranking survey. The empirical analysis indicates significant differences among choice models for different ranks and provides a clear demonstration of the potential for significant biases in simple pooling of ranking data. The empirical results support the hypothesis that the stability of ranking information decreases with decreasing rank for a ranking of 4 alternatives. The best strategy to combine the ranks is to include rank-specific scale and other bias parameters. However, even with this strategy a model combining all of the ranks was rejected. © 1991.