Defining Regressor Variables

Theodore R. Holford

in Multivariate Methods in Epidemiology

Published in print July 2002 | ISBN: 9780195124408
Published online September 2009 | e-ISBN: 9780199864270 | DOI:

Series: Monographs in Epidemiology and Biostatistics

Defining Regressor Variables

Show Summary Details


The coding of categorical variables can result in very different values for the parameters in a regression model, but when they are correctly understood in term of effects on estimates of risk, they do not affect the overall conclusions. This chapter considers two commonly used coding schemes that use either 0 1 values only or -1 0 1. It examines specially defined variables that allow the consideration of thresholds, as well as questions of whether associations are consistent for all subgroups of the population. It also considers an approach for re-expressing either the regressor variable or the response in order to achieve a relationship that can be described by a generalized linear model. Exercises are provided at the end of the chapter.

Keywords: categorical variables; linear hypothesis testing; regression; estimates of risk

Chapter.  12730 words.  Illustrated.

Subjects: Public Health and Epidemiology

Full text: subscription required

How to subscribe Recommend to my Librarian

Buy this work at Oxford University Press »

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.