Have trouble viewing this email? Click here

Propensity Score Methods

An ICTS Research Methods Short Course

Tuesday October 28, 2014, 2:30 pm – 6:00 pm, Nelson Lecture Hall - Irvine

Course Description: In observational studies, randomization of study participants to treatment groups, such as treatment and control groups, is not possible. Differences in the characteristics of treated and non-treated subjects, such as their baseline demographic factors and comorbidities, can result in biased estimates of the treatment effects of interest. Propensity score (PS) methods (e.g., PS matching) can be used to balance differences between treated and non-treated study groups in order to control/reduce this bias. This short course will present the fundamental rationale for PS methods, their application and implementation in major statistical software packages, including SAS, R and Stata.

Learning Objectives: Course registrants will have the opportunity to learn and understand:

  • The differences between randomized control trials (RCT) and observational studies (OS) and selection bias in OS
  • What is the PS and the rationale for PS methods, including matching, stratification and regression adjustment
  • How to estimate the PS and use it in practice
  • Software codes for implementation in major statistical software packages (SAS, R and Stata)

Topics: Selection bias in OS • Goal and definition of PS • PS estimation using logistic regression • PS matching, stratification and regression adjustment • Greedy/local and global/optimal matching algorithms • Distance metrics for matching (Mahalanobis, Euclidean and absolute distances) • Checking covariate balance • Analysis after covariate balance • Worked examples illustrating PS in practice • Implementation in statistical software (SAS primarily, although codes in R and Stata will also be covered)

Prerequisites: a) Basic understanding of the use and interpretation of logistic regression (LR); b) Basic familiarity with statistical software packages (e.g., coding in SAS, Stata or R). If you do not meet these prerequisites, please complete the tutorials below; this will help you achieve the course learning objectives. LR Tutorials:
http://www.ats.ucla.edu/stat/sas/dae/logit.htm
http://www.cdc.gov/nchs/tutorials/nhanes/NHANESAnalyses/LogisticRegression/Info1.htm
http://www.ats.ucla.edu/stat/sas/faq/oratio.htm

Registration Fee: UCI faculty and staff: $75, UCI student: $50, non-UCI registrant: $150 (fee includes lecture notes and coffee break)

To register: http://www1.icts.uci.edu/ccgateway/biostat_ps.cfm

Contact: Sarah Cushing • (714) 456-2313 • scushing@uci.edu

cid:9926c770-6d10-4682-add0-c07bf56c470a@uci.edu

About the Course Instructor: Dr. Nguyen is Professor in the Department of Medicine and Director of the Biostatistics, Epidemiology & Research Design (BERD) Unit, UC Irvine Institute for Clinical and Translational Science. Dr. Nguyen’s research involves several areas of basic, clinical and translational science, ranging from genomics, targeted treatment trials for individuals with Fragile X Syndrome to characterization of outcome risk trajectories in patients on dialysis, such as cardiovascular events and infection-related hospitalization. Stemming from his collaboration on biomedical research studies, Dr. Nguyen develops innovative statistical methods/tools to further clinical and translational science research. Prior to joining UC Irvine in 2013, he was Professor in the Division of Biostatistics, Department of Public Health Sciences, Consortium Statistics Leader for the NeuroTherapeutics Research Institute, Director of the Data Coordinating Center for the Early Autism Risk Longitudinal Investigation (EARLI) Network, and Director of the Statistics Core of the Center for Children’s Environmental Health at UC Davis. He has published over 85 research papers and conducted several observational studies using propensity score.