Classification with discrete and continuous variables via general mixed-data models
Authors:
- 7 February 2011
- journal article
- research article
- Published by Taylor & Francis in Journal of Applied Statistics
- Vol. 38 (5) , 1021-1032
Abstract
We study the problem of classifying an individual into one of several populations based on mixed nominal, continuous, and ordinal data. Specifically, we obtain a classification procedure as an extension to the so-called location linear discriminant function, by specifying a general mixed-data model for the joint distribution of the mixed discrete and continuous variables. We outline methods for estimating misclassification error rates. Results of simulations of the performance of proposed classification rules in various settings vis-à-vis a robust mixed-data discrimination method are reported as well. We give an example utilizing data on croup in children.Keywords
This publication has 21 references indexed in Scilit:
- Discriminant Analysis Using Mixed Continuous, Dichotomous, and Ordered Categorical VariablesMultivariate Behavioral Research, 2007
- General mixed‐data model: Extension of general location and grouped continuous modelsCanadian Journal of Statistics, 2007
- Variable selection in discriminant analysis based on the location model for mixed variablesAdvances in Data Analysis and Classification, 2007
- A generalized Mahalanobis distance for mixed dataJournal of Multivariate Analysis, 2005
- A Randomized Trial of a Single Dose of Oral Dexamethasone for Mild CroupNew England Journal of Medicine, 2004
- The location model for mixtures of categorical and continuous variablesJournal of Classification, 1993
- Maximum Likelihood Estimation of Multivariate Polyserial and Polychoric Correlation CoefficientsPsychometrika, 1987
- Discrimination and Classification Using Both Binary and Continuous VariablesJournal of the American Statistical Association, 1975
- Classification Based on Dichotomous and Continuous VariablesJournal of the American Statistical Association, 1974
- Multivariate Correlation Models with Mixed Discrete and Continuous VariablesThe Annals of Mathematical Statistics, 1961