Proceedings of the Conference on Human and Economic Resources

Recent studies about estimating half-lives of purchasing power parity argues that heterogeneity bias resulting from aggregating the real exchange rate across sectors is important and should be taken into account. However, they do not use appropriate techniques to measure persistence. In this paper we use the extended median-unbiased estimation method in panel context for each sector separately and calculate both point estimates and confidence intervals. We conclude that controlling for sectoral heterogeneity bias and small sample bias will not solve the PPP puzzle.PPP persistence, real exchange rate, heterogeneity bias extended median-unbiased estimation, panel data