Interpretation:
The low p-value thus rejects the null hypothesis that the underlying
distribution is a normal distribution.
I now want to check if there is a difference in the distribution of the
scores from schools which have >0 outlets with
>15 ppb lead contamination and those which have 0 outlets
with > 15 ppb lead contamination.
Since the overall distribution is not parametric, I make use of the Mann
Whitney U test to compare these two distributions: