Dynamic Cost-o¤sets of Prescription Drug Expenditures: Panel Data Analysis Using a Copula-based Hurdle Model

This paper presents a new copula-based approach for analyzing panel data in which (1) the observed multivariate outcomes are a mixture of zeros and continuouslymeasured positives, with the zeros accounting for a nontrivial proportion of the sample; (2) both the zero and positive outcomes show state dependence and dynamic interdependence (cross-equation lagged dependence); and (3) the zeros and the positives display contemporaneous association. The copula-based approach is especially appealing because the contemporaneous associations may involve asymmetric dependence. We apply our methodology to the analysis of cost-o¤sets between prescription drug and other non-drug healthcare expenditures using data from the Medical Expenditure Panel Survey. There is evidence of modest cost-o¤sets of expenditures on prescribed drugs. JEL codes: C51, C33, I11