Article ID: | iaor19931843 |
Country: | United States |
Volume: | 27B |
Issue: | 1 |
Start Page Number: | 65 |
End Page Number: | 78 |
Publication Date: | Feb 1993 |
Journal: | Transportation Research. Part B: Methodological |
Authors: | Kitamura Ryuichi, Goulias G. Konstadinos |
An extensive evaluation of alternative estimation methods for logistic binary choice probabilities when applied to binary frequency data with limit cases is presented in this paper. The methods examined are binomial-logistic (BL) model, Berkson’s (BK) method, and Haldane’s (HL) method. These models are applied to weekly mode choice data that contained a substantial number of limit cases in which one of the alternatives was never chosen. The results indicate that the BL model is a practical tool that outperforms all the other methods examined in this study. The BL models accommodate limit cases without requiring any additional assumptions or approximations. The BK and HL methods have been shown to offer coefficient estimates similar to, and fits that are somewhat worse than, those obtained by the BL models. These methods remain to be useful tools for the analysis of binary frequency data, especially in initial phases of analysis. In this paper it is also shown that coefficient estimates of HL methods are sensitive to the value of the adjustment constant,