Hey guys!

I have an urgent question for my master thesis.

In my thesis, I'm comparing 4 performance metrics. My data consists of 100 funds and I calculated the performance for the funds with the 4 different metrics.
In a next step, I calculated the correlation between the 4 metrics. I used the Spearman method because the performance data for all 4 metrics were not normally distributed. I use R and R gives you the significance levels calculated with a t-test. However, since the data is not normally distributed, I think I cannot use a t-test. I think the solution might be the wilcoxon signed rank test. However, I really don't know how to use it. Like I said, I have a dataset for 100 funds and I calculated the performance for the funds with 4 different metrics. I already calculated the correlations, but I need to tell if the correlations are significant.

I tried the following in R:

wilcox.test(metric1, metric2, paired = T)

the results: Wilcoxon signed rank test with continuity correction

data: metric1 and metric2 V = 74, p-value < 2.2e-16 alternative hypothesis: true location shift is not equal to 0

I'm really confused by the result. A low p-value is against my intuitions and I really think that the (correct) results will be that the correlations are significant.

Thank you for the help and sorry for the essay!