A1401
Title: Flexible Bayesian quantile analysis of residential rental rates
Authors: Mohammad Arshad Rahman - Indian Institute of Technology Kanpur (India) [presenting]
Shubham Karnawat - University of California Irvine (United States)
Ivan Jeliazkov - University of California Irvine (United States)
Angela Vossmeyer - Claremont McKenna College (United States)
Abstract: A random effects quantile regression model is developed for panel data that allows for increased distributional flexibility, multivariate heterogeneity, and time-invariant covariates in situations where mean regression may be unsuitable. The approach is Bayesian and builds upon the generalized asymmetric Laplace distribution to decouple the modeling of skewness from the quantile parameter. An efficient simulation-based estimation algorithm is derived; its properties and performance are demonstrated in targeted simulation studies and employed in the computation of marginal likelihoods to enable formal Bayesian model comparisons. The methodology is applied in a study of U.S. residential rental rates following the Global Financial Crisis. Empirical results provide interesting insights on the interaction between rents and economic, demographic and policy variables, weigh in on key modeling features, and overwhelmingly support the additional flexibility at nearly all quantiles and across several sub-samples. The practical differences that arise as a result of allowing for flexible modeling can be nontrivial, especially for quantiles away from the median.
