 A Comparison of Regression Models for the Analysis of Ordered Categorical DataWerner Holtbrügge and Martin Schumacher Journal of the Royal Statistical Society Series C, 1991, vol. 40, issue 2, 249-259 Abstract: In a clinical trial on the treatment of lung cancer two chemotherapeutic strategies were compared with respect to tumour response, which was assessed under four ordinal categories. Two regression models for the analysis of ordered categorical data, the proportional odds model and the stereotype model, are used to analyse the data. Differences between the models with respect to estimation and significance tests are further investigated using simulation studies. The results indicate that estimates are less biased in the proportional odds model, but in the stereotype model an improvement may be achieved if adjacent categories are amalgamated. Similar behaviour is observed with respect to tests concerning regression coefficients which are of primary interest in most clinical trials. While in the proportional odds model no relevant deviation from the nominal level of significance is observed, comparable results are obtained in the stereotype model only after amalgamation of categories. Date: 1991 Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:bla:jorssc:v:40:y:1991:i:2:p:249-259 Ordering information: This journal article can be ordered from Access Statistics for this article Journal of the Royal Statistical Society Series C is currently edited by R. Chandler and P. W. F. Smith More articles in Journal of the Royal Statistical Society Series C from Royal Statistical Society Contact information at EDIRC. |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.