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

Abstract

This article uses several tests to analyse serial dependence in financial data, trying to confirm the existence of some kind of nonlinear dependence in stock markets. In an attempt to provide a better explanation of the behaviour of stock markets, we used tests based on mutual information and detrended fluctuation analysis (DFA). Applying these tests to the series of stock market indexes of 10 countries, we concluded for the absence of linear autocorrelation. However, with other tests, we found nonlinear serial dependence that affects the rates of return. With DFA, we found out that most return rate series have long-range dependence, which appears to be more pronounced for Spain, Greece and Portugal. To confirm the inefficiency of those markets, based on our results, we should prove the existence of abnormal profits.

The footprints of COVID-19 on Central Eastern European stock markets: an intraday analysis

“…In this paper, we apply Multifractal Detrended Fluctuation Analysis (MFDFA) to evaluate the effects of Covid-19 in terms of the efficiency pattern of three Eastern European stock markets (Czech Republic, Hungary and Poland) compared to other stock markets. MFDFA or related methodologies have been employed by many researchers to study the structural properties of many European stock markets and hence their efficiency levels (Aslam, Mohti et al, 2020;Ferreira, 2018;Ferreira & Dionísio, 2014;Miloş et al, 2020;Onali & Goddard, 2011). We also find similar studies performed during the Covid-19 outbreak involving the use of detrended methods to assess the fractal behaviour of financial markets (Aslam, Mohti et al, 2020;Sharif et al, 2020).…”

“…For these markets, departure from the EMH could be caused by their limited development, compared to other more developed markets. In fact, in developed markets like those used to compare the results in this paper, it is usual to find some evidence against full verification of the EMH (see, for example, Di Matteo et al, 2005or Ferreira & Dionísio, 2014, among many others). However, it is relevant to state that even in the case of evidence against the EMH, some work identifies that some CEEC markets, mainly the three used in this study, have increased their efficiency over time.…”

Non-linear dependencies in African stock markets: Was subprime crisis an important factor?

“…Later studies confirm the behaviour of financial markets as random walks, mainly if the linear behaviour of autocorrelations is studied. This is found in older studies (see, for example, [6,7] or [8]) or even in more recent work (see, for example, [9,10]).…”

“…Muchnik et al [43] analysed the sequence of maxima and minima in stock markets and foreign exchanges and concluded that they present long-term correlation (the authors relating this to volatility clustering). Ferreira and Dionísio [9] used DFA for G7 countries plus Greece, Portugal and Spain, and also found evidence of long-term dependence in almost all indices. Sánchez et al [44] used the Hurst Exponent estimation to study the behaviour of stocks from the S&P500 index.…”

“…Although DFA was created to study the behaviour of DNA [19], it was extended to study other phenomena, including the behaviour of financial series. Studies such as Ferreira and Dionísio [9], Kristoufek [20], Cao and Zhang [21] or Anagnostidis et al [22] are just some examples of relatively recent studies that analyse stock markets using DFA, and also find common evidence of long-term dependence.…”