View in EDS

Analysis of Ordered Categorised Data. Technical Report No. 62. Revised.

Saved in:

Bibliographic Details
Title:	Analysis of Ordered Categorised Data. Technical Report No. 62. Revised.
Language:	English
Authors:	McCullagh, Peter, Chicago Univ., IL. Dept. of Statistics.
Peer Reviewed:	N
Page Count:	64
Publication Date:	1978
Sponsoring Agency:	National Science Foundation, Washington, DC.
Document Type:	Reports - Research
Descriptors:	Data Analysis, Goodness of Fit, Mathematical Models, Multiple Regression Analysis, Research Reports, Scores, Statistical Analysis, Statistical Data
Abstract:	A general class of regression models for ordered categorised data is developed and discussed. Thier properties are contrasted with log linear models and other methods of analysis. The general problem of fitting by maximum likelihood is discussed and solved. The models are shown to be multivariate extensions of generalised linear models and the fitting method is iteratively re-weighted least squares. Special attention is given to a particular model--the cumulative logit model--and alternative fitting methods are described for this case. Applications are discussed with the aid of three examples. (Author/GDC)
Entry Date:	1980
Accession Number:	ED177190
Database:	ERIC

Description
Abstract:	A general class of regression models for ordered categorised data is developed and discussed. Thier properties are contrasted with log linear models and other methods of analysis. The general problem of fitting by maximum likelihood is discussed and solved. The models are shown to be multivariate extensions of generalised linear models and the fitting method is iteratively re-weighted least squares. Special attention is given to a particular model--the cumulative logit model--and alternative fitting methods are described for this case. Applications are discussed with the aid of three examples. (Author/GDC)