Skip to main content
A kernel-based metric for balance assessment
Technical Report (2016)
  • Yeying Zhu, University of Waterloo
  • Jennifer S Williams, The Pennsylvania State University
  • Debashis Ghosh
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 11.0px Helvetica}
One of the commonly used approaches to the causal analysis of observational data is the use
of matching techniques. Matching involves taking treated subjects and nding comparable
control subjects who have either similar covariate values and/or propensity score values.
We focus on the latter approach in this article. In matching, an important purpose is to
achieve balance in the covariates among the treatment groups. In this article, we
propose a new balance measure called kernel distance, which is the empirical estimate of the probability metric
defined in the reproducing kernel Hilbert spaces. Compared to the traditional balance metrics,
the kernel distance measures the difference in the two multivariate distributions instead of the
difference in the finite moments of the distribution. Simulation studies and a real data example are used to
illustrate the methodology.
  • Causal effect; Prohorov metric; probability law; multivariate balance.
Publication Date
Citation Information
Yeying Zhu, Jennifer S Williams and Debashis Ghosh. "A kernel-based metric for balance assessment" Technical Report (2016)
Available at: