# Logistic regression: Analyzing binary outcomes

Home / Research Methods  / Logistic regression: Analyzing binary outcomes

## An overview of our binary logistic regression workshop

Many outcomes in education are binary in nature: accept or decline an offer of admission, pass or fail a course, persist to another year or stop out. Binary logistic regression, rather than multiple regression, is the standard approach to analyzing discrete outcomes. This workshop will train participants in applying binary logistic regression to their research, focusing on 1) the parallels with multiple regression, and 2) how to interpret model results for a wide audience.

## Expected outcomes of our binary logistic regression workshop

By the end of the workshop, participants should understand binary logistic regression well enough to begin using it in their research. They will understand when to use binary logistic regression, how to interpret binary logistic regression coefficients, and how to calculate and discuss model fit.

## Who should attend?

The target audience is researchers who are familiar with multiple regression but are not familiar with binary logistic regression, and wish to begin using it in their research (or those researchers looking for a quick refresher). This is an applied course, so no advanced math skills are required; however, you should understand how to interpret a multiple regression coefficient. If you need a refresher on multiple regression, check out our regression workshop. Software demonstrations will use Stata, but output from SAS and SPSS will be included and reviewed so that participants can understand and interpret binary logistic regression models estimated using these software. If you are interested in propensity score matching, this is an excellent workshop to attend prior to our matching workshop.

SPSS users: You must have the SPSS Regression Module to be able to run a logistic regression model.

## Agenda

1. Why binary logistic regression is preferred over multiple regression (the linear probability model)
2. How binary logistic regression estimates coefficients (maximum likelihood), and the problem this poses for interpretation
3. Similarities with multiple regression: most of what you know can be applied directly to binary logistic regression
4. Predicted probabilities versus Y-hat from multiple regression
5. Interpreting results using odds ratios: what they are and why you don’t want to use them
6. Interpreting results using discrete changes in probability (delta-p statistic)
7. Different ways of measuring model fit (pseudo R-squared, percent correctly predicted)