Are stock prices stationary? Some new evidence from a panel data approach

Purpose – This paper investigates whether mean reversion holds for a panel of 16 OECD stock price indices for the period 1970 to 2011. Design/methodology/approach – We employ seemingly unrelated regression (SUR)-based linear and non-linear unit root tests which are not only able to exploit the power of panel data analysis but also account for cross sectional dependencies as well as identify which panel members are stationary. Findings – In contrast to a literature that offers mixed findings on stationarity, it was found that most of our sample is characterized as mean- or trend-reverting with approximated half-lives in the region of three to five years. Originality/value – In contrast to other panel unit root tests of stock prices, the authors identify which individual panel members are stationary and non-stationary using a SURADF test. A further novelty of our approach is that we also develop a SUR-based panel KSS test that allows us to explore the possibility that stock prices exhibit non-linear stationarity.