Applied Logistic Regression

This Applied Logistic Regression course provides theoretical and practical training for epidemiologists, biostatisticians and professionals of related disciplines in statistical modeling with particular emphasis on logistic regression.

The increasingly popular logistic regression model has become the standard method for regression analysis of binary response data in the health sciences.

By the end of this course, students should

• Master methods of statistical modeling when the response variable is binary.
• Be confident users of the Stata package for computing binary logistic regression models.

This is a hands-on, applied course where students will become proficient at using computer software to analyze data drawn primarily from the fields of medicine, epidemiology and public health.

There will be many practical examples and homework exercises in this class to help you learn. If you fully apply yourself in this course and complete all of the homework, you will have the opportunity to master various methods of statistical modeling and you will become a more confident user of the Stata* package for computing linear, polynomial and multiple regression.

*Access to Stata will be provided at no cost for the duration of this course.




This course was developed in partnership with the Centre Virchow-Villermé for Public Health Paris-Berlin, a bi-national centre of the Université Sorbonne Paris Cité and Charité – Universitätsmedizin Berlin. Special support was contributed from the Université Paris Descartes that also belongs to the community of Université Sorbonne Paris Cité.



All lectures and instructional materials developed for this course by the Ohio State University are licensed under the Creative Commons AttributionNonCommercial-ShareAlike 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by-nc-sa/4.0/

Week One

• Logistic Regression Analysis
• Fitting the Logistic Model

Week Two

• The Likelihood Ratio Test
• Finding a Confidence Interval for β and π
• The Multiple Logistic Regression Model
• Fitting the Multiple Logistic Regression Model

Week Three

• Confidence Intervals for β, the Logit, and π
• Interpretation of Coefficients
• Dichotomous Independent Variables

Week Four

• Polychotomous Independent Variables
• Continuous Independent Variables

Week Five

• Statistical Adjustment
• Interaction and Confounding

Week Six

• Estimating Odd Ratios in the Presence of Interaction
• The 2X2 Table - Stratified Analysis vs Logistic Regression
• Assessing the Fit of the Logistic Regression Model

Week Seven

• Summary Measures of Goodness-of-Fit
• Area Under the ROC Curve

Week Eight

• R-squared-type Measures
• Numerical Problems
• Estimating the Mortality of ICU Patients