scispace - formally typeset
Search or ask a question
Topic

Ordinal regression

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


Papers
More filters
Journal ArticleDOI
TL;DR: A comparison between structural equation modeling and logistic regression for univariate analysis of categorical twin data is presented, finding the two methods to be generally comparable in their ability to detect a “correct” model under the specifications of the simulation.
Abstract: The univariate analysis of categorical twin data can be performed using either structural equation modeling (SEM) or logistic regression. This paper presents a comparison between these two methods using a simulation study. Dichotomous and ordinal (three category) twin data are simulated under two different sample sizes (1,000 and 2,000 twin pairs) and according to different additive genetic and common environmental models of phenotypic variation. The two methods are found to be generally comparable in their ability to detect a "correct" model under the specifications of the simulation. Both methods lack power to detect the right model for dichotomous data when the additive genetic effect is low (between 10 and 20%) or medium (between 30 and 40%); the ordinal data simulations produce similar results except for the additive genetic model with medium or high heritability. Neither method could adequately detect a correct model that included a modest common environmental effect (20%) even when the additive genetic effect was large and the sample size included 2,000 twin pairs. The SEM method was found to have better power than logistic regression when there is a medium (30%) or high (50%) additive genetic effect and a modest common environmental effect. Conversely, logistic regression performed better than SEM in correctly detecting additive genetic effects with simulated ordinal data (for both 1,000 and 2,000 pairs) that did not contain modest common environmental effects; in this case the SEM method incorrectly detected a common environmental effect that was not present.

13 citations

Journal ArticleDOI
TL;DR: Two classes of phenology model that can be applied to discrete development stages of insects and estimated from stage frequency data are described and a class of models based on continuation ratios, which preserves the discrete nature of the development stages, are described.
Abstract: Two classes of phenology model that can be applied to discrete development stages of insects and estimated from stage frequency data are described. First, ordinal regression models, which assume there is an underlying, unobserved, and continuous variable controlling development level; and second, a class of models based on continuation ratios, which preserves the discrete nature of the development stages, are described. Model estimation and testing based on generalized linear modeling methodology are described using a published data set on the phenology of the western spruce budworm, Choristoneura occidentalis Freeman.

13 citations

Book ChapterDOI
12 Jun 2013
TL;DR: A framework for synthetic data generation is developed with special attention to pattern order in the space, data dimensionality, class overlapping and data multimodality, and the full control over data topology and over a set of relevant statistical properties of the data is developed.
Abstract: Synthetic datasets can be useful in a variety of situations, specifically when new machine learning models and training algorithms are developed or when trying to seek the weaknesses of an specific method. In contrast to real-world data, synthetic datasets provide a controlled environment for analysing concrete critic points such as outlier tolerance, data dimensionality influence and class imbalance, among others. In this paper, a framework for synthetic data generation is developed with special attention to pattern order in the space, data dimensionality, class overlapping and data multimodality. Variables such as position, width and overlapping of data distributions in the n-dimensional space are controlled by considering them as n-spheres. The method is tested in the context of ordinal regression, a paradigm of classification where there is an order arrangement between categories. The contribution of the paper is the full control over data topology and over a set of relevant statistical properties of the data.

13 citations

Journal ArticleDOI
TL;DR: In this paper, an alternative (restricted) likelihood ratio test for ordinal predictors with ordered levels is proposed, which is based on the mixed model formulation of penalized dummy coefficients.
Abstract: In a linear model relevance of a categorical predictor with ordered levels is typically tested by use of the standard F-test (known from statistical textbooks). Such a test can also be applied for testing whether the regression function is linear in the ordinal predictor’s class labels. In this paper we propose an alternative (restricted) likelihood ratio test for these hypotheses which is especially suited for ordinal predictors and is based on the mixed model formulation of penalized dummy coefficients. We show in simulation studies that the new test is more powerful than the standard F-test in many situations. The advantage of the new test is especially striking when the number of ordered levels is moderate or large. Using the relationship to mixed effect models and robust existent fitting software obtaining the test and its null distribution is very fast; a fast R implementation is provided.

13 citations

Journal ArticleDOI
TL;DR: The ordinal hierarchical classes model is shown to subsume Coombs and Kao's model for nonmetric factor analysis and an algorithm is described to fit the model to a given data set and is subsequently evaluated in an extensive simulation study.
Abstract: This paper proposes an ordinal generalization of the hierarchical classes model originally proposed by De Boeck and Rosenberg (1998). Any hierarchical classes model implies a decomposition of a two-way two-mode binary arrayM into two component matrices, called bundle matrices, which represent the association relation and the set-theoretical relations among the elements of both modes inM. Whereas the original model restricts the bundle matrices to be binary, the ordinal hierarchical classes model assumes that the bundles are ordinal variables with a prespecified number of values. This generalization results in a classification model with classes ordered along ordinal dimensions. The ordinal hierarchical classes model is shown to subsume Coombs and Kao's (1955) model for nonmetric factor analysis. An algorithm is described to fit the model to a given data set and is subsequently evaluated in an extensive simulation study. An application of the model to student housing data is discussed.

13 citations


Network Information
Related Topics (5)
Regression analysis
31K papers, 1.7M citations
84% related
Linear regression
21.3K papers, 1.2M citations
79% related
Inference
36.8K papers, 1.3M citations
78% related
Empirical research
51.3K papers, 1.9M citations
78% related
Social media
76K papers, 1.1M citations
77% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023102
2022191
202188
202093
201979
201873