1. Duality in balance optimization subset selection
- Author
-
Jason J. Sauppe, Sheldon H. Jacobson, and Hee Youn Kwon
- Subjects
Mathematical optimization ,021103 operations research ,Optimization problem ,Linear programming ,0211 other engineering and technologies ,General Decision Sciences ,Duality (optimization) ,02 engineering and technology ,Management Science and Operations Research ,Boss ,Causal inference ,Covariate ,Theory of computation ,Mathematics - Abstract
In this paper, we investigate a specific optimization problem that arises in the context of Balance Optimization Subset Selection (BOSS), which is an optimization framework for causal inference. Most BOSS problems can be formulated as mixed integer linear programs. By relaxing the integrality constraints so that fractional contributions of control units are permitted, a linear program (LP) is obtained. Properties of this LP and its dual are investigated and a sensitivity analysis is conducted to characterize how the objective value changes as the covariate values are perturbed.
- Published
- 2020
- Full Text
- View/download PDF