Logistic regression finds prediction equation based on independent variables that are used to classify individuals into one of two possible groups. The linear-logistic model is:

P(Y=y2) = 1- P(Y=y1)
This model may be transformed into linear form as follows:

There are two objectives in a logistic regression:
1. Finding a predictive equation for classifying new individuals
2. Interpreting the predictive equation to better understand the relationships that may exist among the variables.
Example: Does depend appearance of serious insurance event (Y) on age (X1), gender (X2), education (X3) and income (X4) of insured? How can insurance company guess from personal information of potential client whether he will or won't have serious insurance event?