 |
• Information Fusion and Complex Event Detection
• Efficient Computation of Social Network Metrics
• Optimal Resource Allocation for Spacial Analysis
• Causal Inference with Observational Data
• Social Network Analysis of Online Smoking Cessation Communities
• Stochastic Modeling of Hospital Readmission Process
• IE 374: Systems Modeling and Optimization: Operations Research II
• IE 575: Stochastic Methods
• IE 411/511: Social Network Behavior Analysis
|
|
|
|
Causal Inference with Observational Data
•Description
•Personnel
| Description |
 |
Scientists in all disciplines attempt to identify and document causal relationships.
Those not fortunate enough to be able to design and implement randomized control experiments
must resort to observational studies. To preserve the ability to make causal inferences outside
the experimental realm, researchers attempt to post-process observational data to mimic experimental
data. The objective of this project is to explore Balance Optimization Subset Selection (BOSS)
as a new paradigm for making causal inference in non-randomized control experiments using
observational data. The primary approach used over the past thirty years effectively attempts
to match individuals in a treatment and a control group to achieve some measure of balance.
An alternative approach investigated here works to eliminate the matching stage and directly
optimize balance; in particular, create sets of statistically indistinguishable treatment
and control groups that are perfectly optimized with respect to one or more pre-defined balance
measures, and hence, produce a minimally biased estimator of the treatment effect. The explored
research directions include modeling with objective functions inspired by conventional multivariate
statistics and information theory, design of methods for the selection of informative covariates, and efficient
algorithm implementation.
|
| Personnel |
|
Collaborators: Dr. Sheldon Jacobson (Computer Science, University of Illinois Urbana-Champaign),
Dr. Wendy Tam Cho (Political Science, University of Illinois Urbana-Champaign),
Dr. Edward Sewell (Mathematics, University of Southern Illinois Edwardsville),
Dr. Murat Kurt (Industrial Engineering, UB)
Students: Lei Sun (Ph.D.), Longsheng Sun (Ph.D.), Chao Lin (M.S.), Zhihao Liu (B.S.)
|
|
