Logistic Regression

Logistic regression allows you to predict a discrete outcome from a set of independent variables that may be continuous, discrete, or binary. The dependent variable is binary/ dichotomous/binominal, i.e., it can take only two values; 0, 1; true, false; Yes, No; success, failure; etc.

With binary variables, ordinary regression methods should not be attempted for several reasons:

• A binary variable can not be normally distributed and hence significance tests and standard errors of regression will be wrong.
• An ordinary regression will permit predicted values outside the 0-1 range.
• The distribution of residual error when a dependent variable is a binary variable is heteroscedastic, and hence violates one of the assumptions of ordinary regression analysis.

Logistic regression in Aabel includes probability and logit (probability). Aabel allows generating:

• Probability charts with one independent variable (see the right-hand side diagram below)
• Probability charts with multiple dimension projections (see the left-hand side diagram below)
• The observed probability can be displayed using markers, as shown in the images below. Probability charts with multiple dimension projections also generate a table of statistics (see the bottom image below).