Nonparametric analysis of the Shenzhen Stock Market: The day of the week effect

Abstract The day of the week effect of the stock market has been studied extensively by researchers. Most of the conclusions previously made were based on parametric models with the assumption of normality. In this article, after examining the null hypothesis of normality of the log-transformed returns from the daily composite index of the Shenzhen Stock Exchange in China from December 25, 1995 to December 31, 2010, we rejected the null hypothesis of normality using three nonparametric tests. We then conducted nonparametric analysis of the transformed data using the Skillings–Mack statistic. The Skillings–Mack statistic is an extension of the well-known Friedman’s test with incomplete observations. We also compared the results based on nonparametric analysis to that from classic parametric models. Our results showed there was a significant negative Thursday effect in the Shenzhen Stock Market during the entire period and several selected sub-periods.

[1]  K. French.  Stock returns and the weekend effect , 1980 .

[2]  Perry Sadorsky,et al.  Day-of-the-week effects in emerging stock markets , 2006 .

[3]  L. Yao,et al.  Market Efficiency and International Diversification: Evidence from India , 2009 .

[4]  Yong Zhou,et al.  Nonparametric estimation of structural change points in volatility models for time series , 2005 .

[5]  T. Kohers,et al.  The disappearing day-of-the-week effect in the world's largest equity markets , 2004 .

[6]  A. Kolmogorov.  On the Empirical Determination of a Distribution Function , 1992 .

[7]  Ruey S. Tsay,et al.  Analysis of Financial Time Series , 2005 .

[8]  G. A. Mack,et al.  On the Use of a Friedman-Type Statistic in Balanced and Unbalanced Block Designs , 1981 .

[9]  Antonio Arcos,et al.  Mean estimation in the presence of change points , 2009, Appl. Math. Lett..

[10]  C. Borror.  Nonparametric Statistical Methods, 2nd, Ed. , 2001 .

[11]  T. Bollerslev,et al.  Generalized autoregressive conditional heteroskedasticity , 1986 .

[12]  C. Kwok,et al.  The day-of-the-week regularity in the stock markets of China , 2001 .

[13]  S. Mehdian,et al.  The Day-of-the-Week Effect in Stock Returns : Further Evidence from Eastern European Emerging Markets , 2004 .

[14]  T. L. Liao,et al.  Day-of-the-week effect in the Taiwan foreign exchange market , 2007 .

[15]  J. Durbin.  INCOMPLETE BLOCKS IN RANKING EXPERIMENTS , 1951 .

[16]  A. Inkeles,et al.  International Encyclopedia of the Social Sciences. , 1968 .

[17]  R. Engle.  Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation , 1982 .

[18]  H. Berument,et al.  The day of the week effect on stock market volatility , 2001 .

[19]  M. Hinich,et al.  INTRADAY PATTERNS IN EXCHANGE RATE OF RETURN OF THE CHILEAN PESO: NEW EVIDENCE FOR DAY-OF-THE-WEEK EFFECT , 2010, Macroeconomic Dynamics.

[20]  M. Stephens.  EDF Statistics for Goodness of Fit and Some Comparisons , 1974 .

[21]  M. Friedman.  The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance , 1937 .

[22]  Douglas A. Wolfe,et al.  Nonparametric Statistical Methods , 1973 .

[23]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .