Course Summary
Credit Type:
Organization's ID:
8 weeks (120 hours)
Dates Offered:
Credit Recommendation & Competencies
Level Credits (SH) Subject
Graduate 3 statistics


The course objective is to focus on a logistic regression approach for analyzing contingency table data, where the cell entries represent counts that are cross-tabulated using categorical variables. It lays the groundwork for logistic regression models for binomial responses and goes on to introduce more complex data structures, e.g. those with more categorical variables or continuous covariates. Students get a broad view of the generalized linear model framework and are also exposed to several model variations. This course is laser-focused on logistic regression modeling and how to interpret these models, rather than the theory behind them.

Learning Outcomes:

  • explain the different components of a generalized linear model
  • Describe logit and probit regression models for binary data, and the difference between them
  • Specify Poisson and logistic regression models, including with categorical predictors
  • Use software to perform regression models
  • Calculate and interpret odds ratio and relative risk
  • Interpret logistic regression models
  • conduct residual analysis
  • demonstrate facility with standard software packages
  • understand the various modeling approaches to categorical data analysis

General Topics:

  • Categorical Responses and Contingency Tables
  • Generalized Linear Models
  • Applications and Interpretations for Logistic Regression
  • Building and Applying Logistic Regression Models
Instruction & Assessment

Instructional Strategies:

  • Audio Visual Materials
  • Case Studies
  • Coaching/Mentoring
  • Computer Based Training
  • Discussion
  • Lectures
  • Practical Exercises
  • Project-based Instruction

Methods of Assessment:

  • Case Studies
  • Examinations
  • Quizzes

Minimum Passing Score:

Supplemental Materials