Logistic Regression Using SAS®: Theory and Application

2.2. Dichotomous Dependent Variables: Example

To make things tangible, let’s start with an example. Throughout this chapter, we’ll be examining a data set consisting of 147 death penalty cases in the state of New Jersey. In all of these cases, the defendant was convicted of first-degree murder with a recommendation by the prosecutor that a death sentence be imposed. Then a penalty trial was conducted to determine whether the defendant would receive a death sentence or life imprisonment. Our dependent variable DEATH is coded 1 for a death sentence and 0 for a life sentence. The aim is to determine how this outcome was influenced by various characteristics of the defendant and the crime.

Many potential independent variables are available in the ...