A limited information estimator for the multivariate ordinal probit model

A limited information estimator for the multivariate ordinal probit model is developed. The main advantage of the estimator is that even for high dimensional models, the estimation procedure requires the evaluation of bivariate normal integrals only. The proposed estimator also avoids the potential problem of encountering local maxima in the estimation process, which is looming using maximum likelihood. The performance of the limited information estimator is shown by Monte Carlo experiments to be excellent and it is comparable to that of the maximum likelihood estimator. Finally, an application of the limited information multivariate ordinal probit to model the consumption level of cigarette, alcohol and betel nut is presented.

[1]  T. Amemiya.  QUALITATIVE RESPONSE MODELS: A SURVEY , 1981 .

[2]  J. Terza,et al.  Producer Attitudes Toward Peanut Market Alternatives: An Application of Multivariate Probit Joint Estimation , 1988 .

[3]  J. Gurland,et al.  Polychotomous Quantal Response in Biological Assay , 1960 .

[4]  Takeshi Amemiya,et al.  The Maximum Likelihood, the Minimum Chi-Square and the Nonlinear Weighted Least-Squares Estimator in the General Qualitative Response Model , 1976 .

[5]  J. R. Ashford,et al.  Computation of the Bi-variate Normal Integral , 1969 .

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

[7]  Zvi Drezner,et al.  Computation of the bivariate normal integral , 1978 .

[8]  D. McFadden.  A Method of Simulated Moments for Estimation of Discrete Response Models Without Numerical Integration , 1989 .

[9]  K. Arnold,et al.  Tables for Computing Bivariate Normal Probabilities , 1958 .

[10]  Joseph V. Ierza.  Ordinal probit: A generalization , 1985 .

[11]  J. R. Ashford,et al.  An Approach to the Analysis of Data for Semi-Quantal Responses in Biological Assay , 1959 .

[12]  David M. Borth.  A Modification of Owen's Method for Computing the Bi-variate Normal Integral , 1973 .

[13]  J. Ashford,et al.  Multi-variate probit analysis. , 1970, Biometrics.

[14]  A. Zellner.  An Efficient Method of Estimating Seemingly Unrelated Regressions and Tests for Aggregation Bias , 1962 .

[15]  Michael T. Hannan,et al.  Age dependence in the mortality of national labor unions: Comparisons of parametric models , 1989 .

[16]  Arnold Zellner,et al.  JOINT ESTIMATION OF RELATIONSHIPS INVOLVING DISCRETE RANDOM VARIABLES , 1965 .

[17]  R. Bargmann,et al.  A Method for the Evaluation of Cumulative Probabilities of Bivariate Distributions using the Pearson Family , 1981 .

[18]  Emmanuel Lesaffre,et al.  Existence and Uniqueness of the Maximum Likelihood Estimator for a Multivariate Probit Model , 1992 .

[19]  John Aitchison,et al.  THE GENERALIZATION OF PROBIT ANALYSIS TO THE CASE OF MULTIPLE RESPONSES , 1957 .

[20]  Strother H. Walker,et al.  Estimation of the probability of an event as a function of several independent variables. , 1967, Biometrika.

[21]  D. R. Divgi.  Calculation of Univariate and Bivariate Normal Probability Functions , 1979 .