Gold and the “weekend effect”

✍ Scribed by Clifford A. Ball; Walter N. Torous; Adrian E. Tschoegl

• Publisher: John Wiley and Sons
• Year: 1982
• Tongue: English
• Weight: 389 KB
• Volume: 2
• Category: Article
• ISSN: 0270-7314
• DOI: 10.1002/fut.3990020209

✦ Synopsis

R 1981) find that average daily return to various financial assets was significantly negative for Monday though positive for the other four days of the week. These results are anomalous since they are inconsistent with the two simplest models of the stock return generating process: the trading time and the calendar time hypotheses. Under both models expected returns for Monday should be positive. The trading time hypothesis implies an identical return distribution across all trading days of the week. The calendar time hypothesis, on the other hand, takes into account the presence of weekends and implies that the mean and variance of the return following these periods should be significantly higher.

The studies cited above considered U S . common stocks (Christie, French, Gibbons and Hess, and Cross), and U S . Treasury bills (Gibbons and Hess). Additionally, Levi (1978) and McFarland, Pettit, and Sung (1981) investigated exchange rates. We examine the return to gold. Gold is widely held, trades almost continuously around the world, and, as we discuss below, provides certain advantages for empirical work.

As with Levi and McFarland et al., while we do find systematic differences in 'The authors would like to thank the anonymous referees of this journal for their comments, Sang-Rim Choi for his research assistance, and Bill Kokontis of the Statistical Department of the Chicago Mercantile Exchange for kindly providing the data.

Clifford A. Ball is an assistant professor of Statistics in the Graduate

School of Business Administration at the University of Michigan. He holds a Ph.D. in mathematics from the University of New Mexico.