首页 | 本学科首页   官方微博 | 高级检索  
     检索      


London calling: Nonlinear mean reversion across national stock markets
Institution:1. Department of Economics, Auburn University, 217 Miller Hall, Auburn, AL 36849, United States;2. Department of Finance and Economics, Georgia Southern University, 621 Coba Dr., Statesboro, GA 30458, United States;1. Department of Mathematics, University of Macau, Macau SAR, China;2. UMacau Zhuhai Research Institute, Zhuhai, China;1. School of Economic Mathematics, Southwestern University of Finance and Economics, Chengdu 611130, PR China;2. School of Finance, Southwestern University of Finance and Economics, Chengdu 611130, PR China;3. Department of Mathematics, Wilfrid Laurier University, Waterloo, Ontario, Canada N2L 3C5
Abstract:This paper revisits empirical evidence of mean reversion of relative stock prices in international stock markets. We implement a strand of univariate and panel unit root tests for linear and nonlinear models of 18 national stock indices from 1969 to 2016. Our major findings are as follows. First, we find strong evidence of nonlinear mean reversion of the relative stock price with the UK index as the reference, calling attention to the stock index in the UK, but not with the US index. Our results imply an important role of the local common factor in the European stock markets. Second, panel tests yield no evidence of linear and nonlinear stationarity when the cross-section dependence is considered, which provides conflicting results from those of the univariate tests. Last, we show how to understand these results via dynamic factor analysis. When the stationary common factor dominates nonstationary idiosyncratic components in small samples, panel tests that filter out the stationary common factor may yield evidence against the stationarity null hypothesis in finite samples. We corroborate this conjecture via extensive Monte Carlo simulations.
Keywords:Unit root test  ESTAR unit root test  Nonlinear panel unit root test  PANIC
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号