Research

Bundle Demand Model for Panel Data with Endogenous Regressors (Job Market Paper) 

Abstract: I propose a Bayesian factor-augmented bundle demand model for panel data, designed to estimate demand as well as the substitutability and complementarity of multiple goods in the presence of endogenous regressors. A factor structure is utilized to model error correlations caused by taste correlation and endogeneity, allowing for time-varying unobserved tastes and utility-price confounders. To demonstrate the merits of the proposed framework, the model is applied to simulated data as well as to estimate the demand for beer and malt beverage in grocery stores. The empirical illustration reveals evidence of price endogeneity and time variation in unobserved tastes and utility-price confounders. Additionally, it suggests that beer products are generally independent in demand, as implied by insignificant cross-price elasticities. The study also confirms a preference for variety, indicated by the increase in bundle effects with family size.

More than Joints: Multi-Substance Use, Choice Limitations, and Policy Implications (Submitted)

Joint with Michelle Sovinsky, Liana Jacobi, and Alessandra Allocca

Abstract: As illicit substances move into the legal product space, substitution patterns with legal products become more salient. In particular, marijuana legalization may have implications for the use of other legal “sin” goods. We estimate a structural model of multi-product use of illegal and legal substances considering joint use, limited access to illicit products, and persistence in use. We focus on a young person’s choice to consume marijuana, alcohol or cigarettes (and possible combinations), and we find that sin goods are complements. Furthermore, our findings emphasize the necessity of accounting for joint consumption and access to obtain correct price sensitivity estimates. Post-legalization, youth marijuana use would increase from 25% to 37%. However, counterfactual results show that a combination of (reasonable) tax increases on all goods along with enforcement against illegal use can potentially revert use to pre-legalization levels. The earlier the tax increases are implemented the more effective they are at curbing future use. Our results inform the policy debate regarding the impact of marijuana legalization on the long-term use of sin goods.

A Flexible Bayesian Random-Coefficients Demand Model

Joint with Dong-Hyuk Kim and Yong Song 

Abstract: This paper introduces a new flexible specification for random coefficients discrete choice model, where the mean utility and instrumental variable (IV) first-stage equations are jointly modeled by a sparse finite mixture of normals, while observed and unobserved individual-level heterogeneity are, as in standard random coefficients multinomial (RCMNP) models, captured by observed consumer characteristics and random coefficients. Our flexible specification have three advantages. First, it relaxes the linear functional form assumption on the mean utility and IV first-stage equation, and provides a local approximation of nonlinear relationships. Second, it relaxes the Gaussian distributional assumption on the joint error of the mean utility (unobserved product characteristics) and first stage equation, which is commonly assumed in Bayesian demand estimation. Third, by limiting the mixture to the mean utility, our specification offers flexibility with parsimony. We provide four simulated examples to illustrate the specification is capable of capturing nonlinear relationships. We apply the new method to household milk demand data to illustrate its feasibility and applicability.

Working paper coming soon.