The day-of-the-week effect on stock returns and volatility: The case of Latin America

Detta är en Magister-uppsats från Lunds universitet/Nationalekonomiska institutionen

Sammanfattning: It has been found that the behavior of stock markets follow patterns that are not necessarily consistent with the Efficient Market Hypothesis. Anomalies have been classified into different groups of which calendar anomalies such as the day-of-the-week effect has been under study for many years. Many authors have been following the evolution of this calendar seasonality in developed stock markets. As for emerging stock markets, investigation has received much less attention. The aim of this paper is to investigate the day-of-the-week effect on stock returns and volatility in four major Latin American stock markets namely, Argentina, Brazil, Chile, and Mexico for the period of 1998 through 2010. The empirical analysis is conducted using three types of time-varying conditional models, namely GARCH, EGARCH, and APARCH assuming two types of distributions. The main findings of this research indicate that evidence of the day-of-the-week seasonality is present in three out of four stock markets. For Chile the anomaly is present on stock returns, for Mexico a clear Monday-effect is observed on stock return volatility, and for Brazil on both. A clear weekend-effect is observed for Chile and Brazil while Friday represents the day with the lowest volatility for Brazil and Mexico. As for Argentina, the same volatility pattern was observed however; the estimated coefficients are statistically insignificant. It is important to point out that results may vary depending on the choice of model with which the anomaly was examined.

  HÄR KAN DU HÄMTA UPPSATSEN I FULLTEXT. (följ länken till nästa sida)