rectly built system, with a relatively high amount of profitable trades, these num-
bers hold very little value and should be looked upon more as freak occurrences
than anything else. Losing streaks will happen even for the most correctly built
system, and sometimes it is good to have many losing trades in a row during the
back testing, because the more losing trades in a row you’ve just experienced (for
real or during back testing), the less likely it is you will go through the same expe-
rience again, provided you’ve done everything else correctly, the logic behind the
system makes sense, and all other system statistics are reliable.
To calculate the likelihood for a certain amount of winning or losing trades in
a row, given a certain amount of trades, you can use the following formula in Excel:
MIN(MAX(0.5^(C$32)*($B4(C$32)1),0),1)
Where:
Cell C3 Winners or losers in a row
Cell B4 Total number of trades
Figure 3.4 shows how this formula can be used to create a matrix, with the
data in the matrix indicating the likelihood for a specific amount of winners or los-40 PART 1 How to Evaluate a System
FIGURE 3.3
Cumulative likelihood of winners and losers.