QQ Plot question related to trading

External question — Cross Validated Stack Exchange Author: Shaun Overton Original post: https://stats.stackexchange.com/questions/152239 License: CC BY-SA 3.0 — https://creativecommons.org/licenses/by-sa/3.0/ Adaptation: HTML converted to plain text; contact email addresses removed. I'm kicking the tires of DSP and don't fully understand the tools. I built an algorithmic trading system and decided to do a Q-Q plot of the signal to noise ratio against the average return for each bin to see if I could eliminate some losing trades. The conclusions that I drew from this are: The distribution is fat-tailed The x-intercept is SNR = 0.10. If I eliminate trades where the SNR < 0.1, the mean return is 0.0004. The mean return for SNR >= 0.1 is 0.0001. I would have expected the opposite based on the Q-Q plot. Since the distribution is fat tailed, is there any simple filter that I can add to focus on the profitable, right tail? What else is this plot saying?

External answer — Cross Validated Stack Exchange Author: KarthikS Original post: https://stats.stackexchange.com/a/152240 License: CC BY-SA 3.0 — https://creativecommons.org/licenses/by-sa/3.0/ Adaptation: HTML converted to plain text; contact email addresses removed. Doesn't 'eliminate trades where the SNR < 0.1' and 'SNR >= 0.1' mean the same thing? I am curious. If you wanted to consider top 50 - percentile trade, just subset for the top 50 percentile directly, I guess. The quantile-quantile (q-q) plot is a graphical technique for determining if two data sets come from populations with a common distribution. How do you wish to find out winning trades by contrasting SNR and percentage return. Isn't that like a 2D scatter plot or something?