时间：2017年3月27日  下午14:30-15:30

地点：邵逸夫科学馆513

题目：Inference in Predictive Quantile Regressions

主讲人：Alex Maynard教授   加拿大圭尔夫大学

主讲人介绍：耶鲁大学PhD，曾执教多伦多大学。研究领域为计量经济学，时间序列。并在the Journal of Econometrics, Econometric Theory, The Review of Economics and Statistics, JBES,CJE,JAE等发表论文多篇。

内容摘要：

This paper studies inference in predictive quantile regressions when the predictive regressor has a near-unit root. We derive nonstandard distributions for the quantile regression estimator and t-statistic in terms of functionals of diffusion processes. We then propose a switching-fully modified (FM) predictive test for quantile predictability with persistent regressors. The proposed test employs an FM style correction with a Bonferroni bound for the local-to-unity parameter when the predictor has a near unit root. It switches to a standard predictive quantile regression test with slightly conservative critical value when the largest root of the predictor lies in the stationary and explosive ranges. Simulations indicate that the test has reliable size in small samples and particularly good power when the predictor is persistent and endogenous, i.e.\ when the predictive regression problem is most acute. We employ this new methodology to test the ability of three commonly employed, highly persistent and endogenous lagged valuation regressors – the dividend yield, earnings price ratio, and book to market ratio -- to predict the median, shoulders, and tails of the stock return distribution.