Ordinal regression

About: Ordinal regression is a research topic. Over the lifetime, 1879 publications have been published within this topic receiving 65431 citations.

Strict two-sided matching method based on complete preference ordinal information

Abstract: The two-sided matching problem has always been one of the hot issues discussed in the fields of economic management and so on. In the two-sided matching problems with complete preference ordinal information,it is more significant to consider the highest acceptable preference ordinal of two-sided agents. However, this kind of two-sided matching problem has not yet received great attention. Hence,a strict two-sided matching method is proposed. In this paper,the related concept on two-sided matching is firstly introduced,and then the two-sided matching problem with the highest acceptable preference ordinal based on complete preference ordinal information is described. In order to solve the problem,the concept and existence theory of strict two-sided matching is given. Considering the satisfaction degree and the lowest acceptable satisfaction degree of two-sided agents,a multi-objective optimization model is developed. By using linear weighted method,the multi-objective optimization model is converted into a single objective model. The matching result is obtained by solving the model. Finally,an illustrative example of two-sided matching between venture investors and venture businesses is given to illustrate the feasibility and validity of the proposed method.

Bayesian semiparametric analysis for latent variable models with mixed continuous and ordinal outcomes

Abstract: Latent variable models with continuous and ordinal responses are a useful tool for interpreting the causal interrelationships among the latent variables and building relations between the latent variables and manifest variables. These models have been successfully applied to many different fields, including behavioral, educational, and social and psychological sciences. However, most developments are constrained within parametric families, of which particular distributions are specified for the parameters of interest. This leads to difficulty in dealing with outliers and/or distribution deviations. In this paper, we propose a Bayesian semiparametric modeling for latent variable model with continuous and ordinal variables. A finite dimensional truncated stick-breaking prior is used to model the distributions of the intercepts and/or covariance structural parameters. Within the Bayesian framework, blocked Gibbs sampler is implemented to deal with the posterior analysis. Moreover, the logarithm of pseudo-marginal likelihood is used to compare the competing models. Empirical results are presented to illustrate the methodology.

Ordinal Logistic Regression with Partial Proportional Odds for Depression Prediction

Abstract: Like many psychological scales, depression scales are ordinal in nature. Depression prediction from behavioural signals has so far been posed either as classification or regression problems. However, these naive approaches have fundamental issues because they are not focused on ranking, unlike ordinal regression, which is the most appropriate approach. Ordinal regression to date has comparatively few methods when compared with other branches in machine learning, and its usage is limited to specific research domains. Ordinal logistic regression (OLR) is one such method, which is an extension for ordinal data of the well-known logistic regression, but is not familiar in speech processing, affective computing or depression prediction. The primary aim of this study is to investigate proportionality structures and model selection for the design of ordinal regression systems within the logistic regression framework. A new greedy based algorithm for partial proportional odds model selection (GREP) is proposed that allows the parsimonious design of effective ordinal logistic regression models, which avoids an exhaustive search and outperforms model selection using the Brant test. Evaluations on the DAIC-WOZ and AViD depression corpora show that OLR models exploiting GREP can outperform two competitive baseline systems (GSR and CNN), in terms of both RMSE and Spearman correlation.