A note on the general elections and long memory: evidence from the London Stock Exchange

Abstract

The efficient market hypothesis (EMH) in the weak-form requires that there is no serial correlation between the returns at different times and successive price changes. On the contrary, stock returns displaying statistically significant autocorrelation between observations widely separated in time, or long memory, would weaken the properties derived from martingale models for pricing derivatives and other financial assets. Using spectral regression method, the fractional differencing parameter is estimated using 522 trading days (2 years post-UK general election day) in the London Stock Exchange (LSE). Evidence suggests that, regardless of the political party forming the government and consistent with findings for major capital markets, there is no evidence to suggest that the market is inefficient in the weak form of the efficient market hypothesis.