手法を比較

	二項分布二変量プロビットモデル	多項ロジスティック回帰	順序ロジスティック回帰 (Ordered Logit/Probit)
分野	計量経済学	計量経済学	計量経済学
系統	Regression model	Regression model	Regression model
提唱年	1970	1974	1980
提唱者	J. R. Ashford & R. R. Sowden	McFadden	McCullagh (proportional odds / cumulative model)
種類	Maximum-likelihood binary outcome model	Multinomial logistic regression	Cumulative ordinal regression
原典	Ashford, J. R., & Sowden, R. R. (1970). Multi-variate probit analysis. Biometrics, 26(3), 535–546.	McFadden, D. (1974). Conditional Logit Analysis of Qualitative Choice Behavior. In P. Zarembka (Ed.), Frontiers in Econometrics (pp. 105-142). Academic Press. ISBN: 978-0127761503	McCullagh, P. (1980). Regression Models for Ordinal Data. Journal of the Royal Statistical Society: Series B, 42(2), 109-142.
別名	Bivariate Binary Probit, Joint Probit Model, Two-Equation Probit, İki Değişkenli Probit	multinomial logistic regression, polytomous logistic regression, softmax regression, Çok Kategorili Lojistik Regresyon	ordinal logistic regression, proportional odds model, cumulative logit model, ordered probit
関連	3	5	4
概要	The Bivariate Probit Model, introduced by Ashford and Sowden (1970), jointly estimates two binary outcome equations whose error terms are allowed to be correlated. By modeling both outcomes simultaneously under a bivariate normal distribution, it corrects for the dependence between decisions that separate probit regressions would ignore, producing consistent and efficient parameter estimates for researchers studying interrelated binary choices.	Multinomial logistic regression is a maximum-likelihood method for a nominal (unordered) dependent variable with more than two categories. Building on McFadden's 1974 treatment of qualitative choice, it gives each category its own set of coefficients relative to a reference category.	Ordered logit is a cumulative regression model for an ordinal dependent variable, fitting a logit (or probit) link to the cumulative category probabilities. Developed in McCullagh's 1980 treatment of regression models for ordinal data, it is the standard tool for Likert-scale, rating, and ranked outcomes.