This thread will look at the effect of day of week in different markets. The day of week effects were made popular by Larry Williams 20 years ago. The question is do this relationships still work and can they be used in developing trading systems even today?. In this thread I will discuss in detail how the day of week effects have evolved over time and are there any relationship which are still tradable in various markets.
Discussions of this concept are not meaningful. They do or they don't. Pound the most recent 5 years of S&P (or other instrument) through the computer. See if they still hold up or not for an instrument. It is called a "study." What people believe is irrelevant. And you have to avoid falling into the seasonal tendency trap. Run 100,000 different instrument-day comboes through the computer, and some will SEEM tradeable. You have to perform validation analysis on them to ensure they are not just those that look good from simple probability that SOME must be on top.
I can see your view that day of week effect could be viewed as number crunching,but day of week is special and what people believe does matter. In my research on day of week effect in the S&P500 which I originally did back in 1995, I found that Monday had an upward bias and Friday downward bias. I published this originally in my newsletter back then, so I guess for these relationships these biases have a lot of out of sample testing. Belief does have a place because Monday and Friday relationships are based oh human nature. The Monday ,Friday bias has a lot to do with the fear since the crash of 1987, that is when these relationships really got strong. People don't want to hold over the weekend and they buy positions back on Monday. I think 911 reinforced this behavior. Remember markets are a measure of mass psychology and that is why beliefs of the masses are important.
Beliefs may matter for a survey but people's actual actions are what determine profit/loss. I believe you'd want to trade on their actions .... If number-crunching showed one thing & beliefs another, only the number crunching would help the P/L... R
Historically , on a open to close basis , Monday's in the S&P500 has a upward bias and Friday a downward one. If we just simply buy at the open on monday in S&P500 and exit on the close your average trade is $114.72. Selling on Friday's open and exiting on the close offers $32.93 a trade. This is from 4/22/1982 to date. This is due to people not wanting to hold over the weekend and having to rebuy the position monday morning. These are not tradable effect but are statically significant
Correct. The market results express beliefs. That is what might be tradeable. Trying to poll people will yield unreliable values. If the market on average goes up on Monday, and people think it goes down, well, that just proves the point
Murray, I sincerely hope that all ET traders believe you (that would be about 5% of the total population). Could you also possibly assert for me that it works especially well for NQ?
I used the big Nasdaq contract from 1996 forward. Here are the dollar values for buying at the open and exiting on the close for a given day of week. You can notice that Friday is negative for both Nasdaq and S&P500, but not Monday. This was run without any filters. Does the effect of SP/Nasdaq Spreads which are trade by large funds have something to do with this ?. Another reason is the Nasdaq collapsed was due to a bubble , over 80% decline, while Dow and S&P500 declines where more orderly from 2000 to 2002. Monday Average Trade $-48.469785575048 Tuesday Average Trade $-353.58035714286 Wednesday Average Trade $110.23214285714 Thursday Average Trade $218.63471971067 Friday Average Trade $-123.90858208955
But what about "black swans"? When the market moves up on Friday with a move enough to wipe out any previous gains using this strategy. Same thing when the market makes a big move down on Monday. Any data on those events? ---------------------------- ForexGuru