August 2009
Intermediate to advanced
648 pages
17h 35m
English
The previous examples have been concerned with analyses of dichotomous outcomes when the explanatory variables were also dichotomous. However, explanatory variables can be nominal (qualitative) with three or more levels, ordinal, or continuous. Logistic regression allows for any combination of these types of explanatory variables. This section is concerned with handling explanatory variables that are qualitative and contain three or more levels.
The following data come from a study on urinary tract infections (Koch, Imrey, et al. 1985). Investigators applied three treatments to patients who had either a complicated or uncomplicated diagnosis of urinary tract infection. Since complicated cases of urinary ...
Read now
Unlock full access