论文信息 - Multiple roots of the Tobit log-likelihood

Multiple roots of the Tobit log-likelihood

Abstract We show that the occurence of multiple roots of the Tobit log-likelihood function in the untransformed parameter space is not nearly so likely as heretofore accepted. The conditions which must be met for them to occur require data configurations which could not be met in random sampling. Moreover, to find a ‘second root’ in practice would require computer programs far more accurate than those which currently exist. Similar results are obtained for a number of other limited dependent variable models.

William H. Greene | W. Greene

[1] Mark B. Stewart,et al. On Least Squares Estimation when the Dependent Variable is Grouped , 1982 .

[2] Masao Nakamura,et al. Part-Time and Full-Time Work Behaviour of Married Women: A Model with a Doubly Truncated Dependent Variable , 1983 .

[3] J. Pratt. Concavity of the Log Likelihood , 1981 .

[4] Jerry A. Hausman,et al. Social Experimentation, Truncated Distributions, and Efficient Estimation , 1977 .

[5] C. Orme. A Note on the Uniqueness of the Maximum Likelihood Estimator in the Truncated Regression Model , 1989 .

[6] R. McKelvey,et al. A statistical model for the analysis of ordinal level dependent variables , 1975 .

[7] Takeshi Amemiya,et al. Regression Analysis when the Dependent Variable is Truncated Normal , 1973 .

[8] J. Heckman. Sample selection bias as a specification error , 1979 .

[9] S. Goldfeld,et al. Maximization by Quadratic Hill-Climbing , 1966 .

[10] J. Greenstadt. On the relative efficiencies of gradient methods , 1967 .

[11] R. Olsen,et al. Note on the Uniqueness of the Maximum Likelihood Estimator for the Tobit Model , 1978 .

[12] P. Dhrymes. Limited dependent variables , 1986 .