How to Test Significance of Trading Strategy? I am wanting to try out a new trading strategy, and it has proven successful on a simulator for the past few days. I do want to collect some more data and see if my results are statistically significant (ideally using a t-test), but I don't really know how to approach this (don't know what I would compare my trades to, or how I would set a 'control' trade).
Any help would be appreciated! Don't have a big background in stats, so go easier with the terminology, but I do have a strong background in other areas of math, so somewhat complex ideas are fine.
 A: Here are some numerical examples to illustrate my comment:
Data sampled using R:
set.seed(2020)
x = round(rexp(5,.001),2)
x
[1]  293.81 1270.05  237.00  739.85 1419.52
summary(x)
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  237.0   293.8   739.9   792.0  1270.0  1419.5 

One-sample t test (not valid because data not normal):
t.test(x)

    One Sample t-test

data:  x
t = 3.2591, df = 4, p-value = 0.03111
alternative hypothesis: true mean is not equal to 0
95 percent confidence interval:
  117.2924 1466.7996
sample estimates:
mean of x 
  792.046 

Nonparametric one-sample Wilcoxon test. P-value 0.0625 (smallest possible
for $n = 5);$ not significant at 1% level.
wilcox.test(x)

        Wilcoxon signed rank test

data:  x
V = 15, p-value = 0.0625
alternative hypothesis: true location is not equal to 0

From Minitab, a sign test (same data): Also gives P=value 0.0625.
Sign Test for Median: Gain 

Sign test of median =  0.00000 versus ≠ 0.00000

      N  Below  Equal  Above       P  Median
Gain  5      0      0      5  0.0625   739.9

