I have not read the paper yet, but the researchers look credible.
Abstract: We find strong lunar cycle effects in stock returns. Specifically, returns in the 15 days around new moon dates are about double the returns in the 15 days around full moon dates. This pattern of returns is pervasive; we find it for all major U.S. stock indexes over the last 100 years and for nearly all major stock indexes of 24 other countries over the last 30 years. In contrast, we find no reliable or economically important evidence of lunar cycle effects in return volatility and volume of trading. Taken as a whole, this evidence is consistent with popular beliefs that lunar cycles affect human behavior. http://papers.ssrn.com/sol3/papers.cfm?abstract_id=281665 Conclusion and suggestions for future research This paper documents a lunar cycle effect in stock returns around the world. Returns around new moon dates are about double the returns around full moon dates. This pattern of returns is pervasive. We find it for all major U.S. stock indexes over the last 100 years and for nearly all of 24 other countries analyzed over the last 30 years. 23 The economic magnitude of the new moon/full moon difference is large, with annualized differences on the magnitude of 5 to 10 percent, rivaling and probably exceeding the market risk premium. However, we find no reliable evidence of lunar cycle effects in return volatility or volume of trading. Similar to the Monday effect, the nature of the lunar cycle effect in returns makes it unlikely that it will translate into exploitable trading strategies. However, the lunar cycle effect is intriguing because it provides strong new evidence about a link between stock prices and human behavior that is difficult to fully explain in terms of traditional economic thought. Some of our preliminary findings also suggest possible future areas for exploration. For example, we find some evidence of lunar cycle effects in bond prices and interest rate changes. However, this evidence is mixed and rather limited, suggesting that it might be useful to expand the investigation to larger samples and a wider array of asset prices (e.g., commodities, futures, and options). Since realized stock returns reflect unexpected changes in expectations, another possibility is to investigate whether changes in analysts' forecasts are more optimistic during new moon than in full moon periods. Such additional evidence would sharpen our understanding of the magnitude and the causes of the lunar cycle effect and offer links and implications to the wider world of finance and economics. Finally, the evidence from stock returns differs from the conclusions of the lunar cycle literature in psychology and medicine. The consensus in this literature is that there is no reliable relation between lunar cycles and human behavior. However, most of these studies investigate deviant and fairly extreme behavior and rely on limited samples, often on the magnitude of a few dozen to a few hundred observations. This approach 24 potentially results in low statistical power, especially if lunar cycle effects on human behavior exist but are fairly mild. In contrast, the evidence in this study relies on stock price indexes, which aggregate routine investment decisions of hundreds of millions of people over periods ranging from dozens of years to over one hundred years. The difference in findings suggests that it might be fruitful to explore new approaches to identifying a link between lunar cycles and human behavior. For example, the evidence in this study suggests that people are more optimistic during new moon periods than in full moon periods. This evidence could be used to design controlled experiments that investigate for predictable changes in relative optimism as a function of the lunar cycle. To subscribe, send a message to: [EMAIL PROTECTED] Or go to: http://groups.yahoo.com/group/FairfieldLife/ and click 'Join This Group!' Yahoo! Groups Links <*> To visit your group on the web, go to: http://groups.yahoo.com/group/FairfieldLife/ <*> Your email settings: Individual Email | Traditional <*> To change settings online go to: http://groups.yahoo.com/group/FairfieldLife/join (Yahoo! ID required) <*> To change settings via email: mailto:[EMAIL PROTECTED] mailto:[EMAIL PROTECTED] <*> To unsubscribe from this group, send an email to: [EMAIL PROTECTED] <*> Your use of Yahoo! Groups is subject to: http://docs.yahoo.com/info/terms/
