Empirical analysis of time-lagged cross-correlations in the Norwegian Stock Market. A discussion of the Efficient Market Hypothesis

Abstract

In this thesis we challenge the existence of weak efficiency in the Norwegian Stock Marked, by analysing time-lagged cross-correlations between log-return series from 811 stocks listed on the Oslo stock exchange and by creating prediction strategies based on the discovered patterns. We limit the strategies to predicting the direction of the movements of the time series only, i.e. either generating a “buy” or a “sell” signal. We use separate time periods, mainly focusing on two-year periods within the timeframe 2006-2015, and do approximately 80 000 Monte Carlo simulation-tests in each of them. The strategy is tested on real, unexamined data. Our results strongly indicate that information based trading strategies give higher returns and entail lower risk, than random, but similarly constructed strategies. Most of our analysis is conducted on data from the period January 1st 2006 to July 1st 2015, and we use the period July 1st 2015 to July 1st 2016 as our testing period.