The End Of Week Affect??

I've just (12/02/12) finished updating my Spread Sheet to include a DOW ("Day Of Week") function. It's been on my list of things to do for a while but the last couple of weeks' results encouraged me to do it sooner rather than later.


The hypothesis is that I'm giving back money/under-performing at the end of the week. This has been especially evident these past couple of weeks, but I wanted to find out if the data added any weight to this idea...


What did I find?


The above charts are all derived from my trades year-to-date. The first chart represents all trades taken between- and including- Monday (Sunday evening..) and Wednesday. The second shows what the equity curve looks like if we use trades taken on a Thursday and Friday. Finally, we have the actual equity curve.

I've marked off two arbitrary dollar values, +$X and -$X, to give context as the scaling of the charts isn't the same and, without those reference points, it'd be impossible to make any comparisons (as dollar values have been removed).

A few facts:

* 17.2% of Nov profits came from Thur and Fri, under-performing the random 40%.
*30% of Dec losses came from Thur and Fri, out-performing the random 40% (ie losing less).
* 66% of YTD's Mon-Wed profits have been lost between Thu and Fri.

So, it would appear that when doing very well I make less at the end of the week. When doing well, I lose and, when losing, I actually do better at the end of the week.

There are a load of potential psychological reasons for these tendencies, but what's most important is how I circumvent this to further sharpen the edge. As far as solutions go, an obvious one is simple to trade more at the beginning of the week than at the end. But I'm tackling one issue at a time so it'll have to get in line for now!

Will collect more data and make any adjustments in the not-too-distant future should it continue to show me this pattern.