Comparing systems with small and big sample sizes

[naf1151]

Lets says I have three system:

2700 game sample ROI 15%
270 game sample ROI 15%
27 game sample ROI 15%

I would obvious play higher units on the first system because its more proven, less on the second and so on.
Is there a formula if I want to of scale these system against each other using my sample size and ROI ?

[Juret]

search for z-scores, it will tell how significant each result sample is