Bivariate logistic regressions are used to test the influence of a normal independent variable on the outcome of a normal dependent variable.

Multinomial logistic regression allows for more than two categories of the dependent variable and thereby uses multiple independent variables to predict the dependent variables' categorical membership.

A regression analysis where predictor variables are entered or removed methodically to find the "best" final model. Whether variables are entered or removed is based on tests of statistical significance.

Logistic regression examines the association between continuous independent variables (i.e., constructs measured on a continuous scale like 1 to 5) and categorical dependent variables (i.e., constructs categorized into groups rather than on a continuous scale). An example of a logistic regression may be whether age (as a continuous variable) predicts Service members’ retention in the military through retirement (categorical, yes/no, outcome).