The advantage of logistic multiple regression over sim-
ple multiple regression is that, through the addition of an
appropriate link function to the usual linear regression
model, the variables may be either continuous or categori-
cal or any combination of both types. Moreover, when the
dependent variable has only two groups, logistic multiple
regression may be preferred over discriminant analysis that
is also can use categorical data for several reasons. First,
discriminant analysis relies on strictly meeting the assump-
tions of multivariate normality and equal variance-covari-
ance matrices across groups-assumptions that are no met in
many situations.