Propensity Score Methods Course

March 9 – 11, 2017
Atlanta, Georgia
Embassy Suites by Hilton

Payment Options

Statistics Course Objectives

The 3 day mini-camp on Propensity Score Methods will enable participants to:

  • Familiarize participants with Rubin’s causal model and the assumptions underlying propensity score methods
  • Guide participants through the steps for implementing multiple versions of propensity score weighting, stratification and matching
  • Provide participants with an understanding of the strengths and limitations of each method and best practices for their use.

Course Syllabus

Thursday March 9, 2017
9:00-9:30 Welcome and introductions
9:30-11:00 Rubin’s Casual Model Break
11:00-11:15 Snack and refreshment break
11:15-12:30 Next Topic
12:30-1:30 Lunch Break
1:30-5:00 Steps of Propensity Score Methods
Friday March 10, 2017
9:00-10:30 Data Preparation for Propensity Score Analysis
10:30-10:45 Break
10:45-12:30 Propensity Score Estimation
12:30-1:30 Provided Lunch Break
1:30-3:00 Propensity Score Weights
3:00-3:15 Snack and refreshment break
3:15-5:00 Estimation With Propensity Score Weights and Sensitivity Analysis
5:30 Optional Reception
Saturday March 11, 2017
9:00-10:30 Propensity Score Stratification
10:30-10:45 Snack and refreshment break
10:45-12:30 Marginal Mean Weighting Through Stratification
12:30-1:30 Provided Lunch break
1:30-3:00 Propensity Score Matching Methods
3:00-3:15 Snack and refreshment break
3:15-5:00 Estimation With Matched Samples and Sensitivity Analysis
5:30 Optional Reception

Why Should You Attend?

  • Get 1 on 1 Consultation With Instructor
  • Professional Networking
  • Peer Socializing
  • Collaboration
  • All Course Resources
  • Breakfast (For Students Staying At Venue Hotel)
  • Lunch, and All-Day Tea/Coffee/Snack Service
  • After Class Networking Mixers

Statistical Methods Course Description

Overview: This workshop will cover the theory and implementation of propensity score methods for removing selection bias in analyses to estimate the effects of programs or conditions with non-experimental data.  The multiple steps required for using propensity score methods will be detailed and implemented with real datasets from national surveys. Code and packages in the R statistical software for propensity score estimation, covariate balance evaluation, treatment effect estimation and sensitivity analysis will be demonstrated. The workshop will cover propensity score weighting, stratification and matching to estimate the average treatment effect and the average treatment effect on the treated.

Instructor: Walter L. Leite

is Associate Professor in the Research and Evaluation Methodology of College of Education at University of Florida. His research program consists of developing and evaluating statistical methods to strengthen causal inference and understanding of causal mechanisms using non-experimental data. He addresses obstacles to effective program evaluation with non-experimental data such as selection bias, measurement error, and attrition bias. He is the author of the book “Practical Propensity Score Methods Using R” published by Sage in 2016. Over the last 10 years, he has published 40 peer-reviewed articles and served as PI, co-PI, or program evaluator on 11 external grants, totaling over $18.9 million in funding.

Additional Information

https://study.sagepub.com/leite

Propensity Score Methods Seminar Walter Leite