Author Description

It is of common interest in medicine to determine whether a hospital meets a benchmark created from an aggregate reference population, after accounting for distributional challenges in multiple covariates. Due to the difficulties of collecting individual-level data, however, it is often the case that only marginal distributions of the covariates are available, making covariate-adjusted comparison difficult. We propose and evaluate a novel approach for conducting covariate-adjusted comparisons when only marginal covariate distributions of the studied hospital are known, but complete information is available for reference hospitals. Our novel approach combines and extends existing methods which are traditionally unrelated both to each other and to the medical problem of interest. These methods include Iterative Proportional Fit, which estimates the cells of a contingency table when only marginal sums are known, and Synthetic Control Methods, which extract information from a dataset when not all collected data points are equally representative of samples from the studied population. Our novel methods are used to estimate hospital-level standardized incidence ratios for comparing the adjusted prevalence of high dose computed tomography examinations relative to a reference standard and are evaluated using simulation studies.