Daily Speculations The Web Site of Victor Niederhoffer & Laurel Kenner Dedicated to the scientific method, free markets, deflating ballyhoo, creating value, and laughter;  a forum for us to use our meager abilities to make the world of specinvestments a better place.

Home

Write to us at: (address is not clickable)

Method in the Markets

3/18/2004
Tom Ryan on Regression Biases
(a good reason to read Stephen Stigler's "Regression Toward the Mean and the Study of Change" )

Regarding the question of whether the month of March is unlucky, one is reminded of the quote attributed to the author of Huck Finn. Yes it is true that in the past unforeseen events have affected the market in the month of March, it is also true that unforeseen events have affected the market in the past in every month at one time or another.

One good rule it seems to me is to always be careful about drawing conclusions from the small sample, or focusing on a select few data points out of a series, no matter what the additional causal relation that we would choose to use to do the selecting. Despite Caesar being murdered by Brutus in the month of March, and the bad portents of the latest stock market moves (either up or down, as both are equally used to support doom by the bears), the Dow, 1950-present, has had a mean return of 1.9% in the month of March with a std dev of 3.9. This is in contrast to a mean return of 0.6%, std dev of 4.1, for all months since January 1950. Other time periods and samples may yield different results, however.

A second good rule it seems to me is that no matter how we may be tempted by our selective memories, that it is most difficult, as Victor has written in both of his books, to ascribe market movements to any one particular news item, and in any case time spent on determining the causal relation between the latest stock market move and a previously released news item, is time spent wasted because it is a retrospective backward looking approach, rather than a forward looking approach as per the latin, specularae. It seems to me that a speculator's time is better spent making an assumption and testing the subsequent hypothesis, than to spend time proving an unprovable assumption.