Estimating Demand Elasticities in Non-Stationary Panels: The Case of Hawaii's Tourism Industry

Tourism demand elasticities are central to marketing, forecasting and policy work, but the wide array of occasionally counterintuitive estimates produced by existing empirical studies implies that some of those results may be inaccurate. To improve the precision of estimates, it is natural to turn to the richness of panel data. However, panel estimation using non-stationary data requires careful attention to the likely presence of common shocks shared across the underlying macroeconomic variables and across regions. Several recently developed econometric tools for panel data analysis attempt to deal with such cross-sectional dependence. We apply the estimator of Pesaran (2006) and Kapetinos, Pesaran and Yamagata (2010) to obtain tourism demand elasticities in non-stationary heterogeneous dynamic panels subject to common factors. We study the extent to which tourism arrivals from the US Mainland to Hawaii are driven by fundamentals such as real personal income and the cost of the trip, and we nd that neglecting cross-sectional dependence in the data leads to spurious results.