Mean reversion in stock prices: new evidence from panel unit root tests
Abstract
Purpose
There are several studies that investigate evidence for mean reversion in stock prices. However, there is no consensus as to whether stock prices are mean reverting or random walk (unit root) processes. The goal of this paper is to re‐examine mean reversion in stock prices.
Design/methodology/approach
The authors use five different panel unit root tests, namely the Im, Pesaran and Shin t‐bar test statistic, the Levin and Lin test, the Im, Lee, and Tieslau Lagrangian multiplier test statistic, the seemingly unrelated regression test, and the multivariate augmented Dickey Fuller test advocated by Taylor and Sarno.
Findings
The main finding is that there is no mean reversion of stock prices, consistent with the efficient market hypothesis.
Research limitations/implications
One issue not considered by this study is the role of structural breaks. It may be the case that the efficient market hypothesis is contingent on structural breaks in stock prices. Future studies should model structural breaks.
Practical implications
The findings have implications for econometric modelling, in particular forecasting.
Originality/value
This paper adds to the scarce literature on the mean reverting property of stock prices based on panel data; thus, it should be useful for researchers.
Keywords
Citation
Narayan, P.K. and Narayan, S. (2007), "Mean reversion in stock prices: new evidence from panel unit root tests", Studies in Economics and Finance, Vol. 24 No. 3, pp. 233-244. https://doi.org/10.1108/10867370710817419
Publisher
:Emerald Group Publishing Limited
Copyright © 2007, Emerald Group Publishing Limited