{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

regression models for ordinal responses a review of methods

regression models for ordinal responses a review of methods...

Info icon This preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
In the study of the dependence of a response variable on a set of independent variables, the choice of a model is largely determined by the scale of measurement of the response. 1 Epidemiologists are often interested in es- timating the risk of adverse events originally measured on an interval scale (such as birthweight), but they often choose to divide the outcome into two or more cat- egories in order to compute an estimate of effect (risk or odds ratio). Similarly, response variables originally measured on an ordinal scale (e.g. severity of pre- eclampsia: none, mild, severe) are often categorized into several binary variables during statistical analysis. Consider, as a motivating example, the data set de- scribed in Table 1. This data is derived from a clinical trial of a single-dose, post-operative analgesic clinical trial. 2 A series of four drugs, denoted by C15, C60, Z100, and EC4 were randomized to patients. The patient responses to the drug were recorded on a five- level ordinal scale (poor, fair, good, very good and ex- cellent). Counts for the most favourable responses, ‘very good’ and ‘excellent’, were amalgamated into one category (‘very good’) due to sparse cell counts. The two drugs Z100 and EC4 were found to be quite similar and together rated better than the pair C15 and C60. 2 The drugs C15 and C60 are the same drug, but vary in their potency. Usually, such data are analysed by creating dichotomies among the levels of the response variable. Possible dichotomies include comparing ‘very good’ to ‘poor’, ‘good’ to ‘poor’, and so on. Standard regression procedures, such as the logistic regression, can then be utilized for data analyses. Although such approaches are not incorrect, they often result in a loss of information due to collapsing (or ignoring) some categories of the response (unless 1323 International Journal of Epidemiology © International Epidemiological Association 1997 Vol. 26, No. 6 Printed in Great Britain * The Center for Perinatal Health Initiatives, Department of Obstetrics, Gynecology and Reproductive Sciences, University of Medicine and Dentistry of New Jersey, Robert Wood Johnson Medical School, 125 Paterson St, New Brunswick, NJ 08901–1977, USA. Department of Epidemiology, The Rollins School of Public Health, Emory University, Atlanta, GA, USA. Regression Models for Ordinal Responses: A Review of Methods and Applications CANDE V ANANTH* AND DAVID G KLEINBAUM Ananth C V (The Center for Perinatal Health Initiatives, Department of Obstetrics, Gynecology and Reproductive Sciences, University of Medicine and Dentistry of New Jersey, Robert Wood Johnson Medical School, 125 Paterson St, New Brunswick, NJ 08901–1977, USA) and Kleinbaum D G. Regression models for ordinal responses: A review of methods and applications. International Journal of Epidemiology 1997; 26: 1323–1333.
Image of page 1

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern