We illustrate
the application of logistic regression in Example
1: Gallstones (Lee
et al., 1995). For categorical variables, polytomous
logistic regression models can be used. When an ordering is
present, special types of polytomous models may be chosen (Harrell
et al., 1998).
For survival
variables, analyses are often performed with Kaplan-Meier curves.
Figure
4.2: Kaplan-Meier Survival Curves
|
|---|
|
Illustration
of Kaplan-Meier survival curves. The observed survival
is shown for four disease groups until five years after hospitalization.
The five-year survival is around 10% for patients hospitalized with
coma or cancer, and around 35% for patients for the other disease groups.
The data are from a random sample of 1000 patients in the SUPPORT study
(Knaus
et al., 1995); http://hesweb1.med.virginia.edu/biostat/s/data/.
|
|
Kaplan-Meier
curves have advantages and disadvantages.