Testing serial dependence in the stock markets of the G7 countries, Portugal, Spain and Greece

This paper utilizes several tests to analyze serial dependence in financial data. In an attempt to provide a better explanation of the behavior of financial markets, we utilized tests that make use of mutual information and developed a detrended fluctuation analysis (DFA). Applying these tests to the series of stock market indexes of 10 European countries, we concluded for the absence of linear autocorrelation. However, with other tests, we found nonlinear serial dependence that affects the rates of return. Our results of mutual information and global correlation based tests confirmed such results. With DFA, we found out that most return rates series have long-range dependence, which appears to be more pronounced for Spain, Greece and Portugal. These conclusions could imply possibility of prediction in those series and thus the violation of the efficient market assumption.