flairCat          count   mean    sd median   IQR   min   max     var
  <fct>             <int>  <dbl> <dbl>  <dbl> <dbl> <int> <int>   <dbl>
1 Group 1           13798 182.   690.      3    26      0 15085 475862.
2 Group 2           29006  79.5  474.      2     7      0 18469 224750.
3 Group 3            1331 116.   424.      4    30      0  8567 179995.
4 Group 4            9514 135.   522.      7    50      0 14444 272759.
5 Group 5           15261 142.   600.      3    22      0 16098 360082.
6 Group 6              82 577.   707.    306.  691.     0  4194 499555.
7 Group 7           40878   5.28  79.0     1     2      0 10407   6233.
8 Group 8            5425 161.   783.      7    59      0 44037 613637.

> kruskal.test(karma ~ flairCat, data=eightFlairs)

    Kruskal-Wallis rank sum test

data:  karma by flairCat
Kruskal-Wallis chi-squared = 11806, df = 7, p-value < 2.2e-16

>pairwise.wilcox.test(eightFlairs$karma,eightFlairs$flairCat,p.adjust.method="BH")

    Pairwise comparisons using Wilcoxon rank sum test

data:  eightFlairs$karma and eightFlairs$flairCat

           Group 1           Group 2    Group 3 Group 4 Group 5 Group 6 Group 7
Group 2    < 2e-16           -          -       -       -       -       -
Group 3    3.6e-06           < 2e-16    -       -       -       -       -
Group 4    < 2e-16           < 2e-16    2.2e-09 -       -       -       -
Group 5    0.12              < 2e-16    3.6e-05 < 2e-16 -       -       -
Group 6    < 2e-16           < 2e-16    < 2e-16 < 2e-16 < 2e-16 -       -
Group 7    < 2e-16           < 2e-16    < 2e-16 < 2e-16 < 2e-16 < 2e-16 -
Group 8    < 2e-16           < 2e-16    3.6e-10 0.23    < 2e-16 < 2e-16 < 2e-16

> oneway.test(karma ~ flairCat, data=eightFlairs, var.equal=FALSE)

    One-way analysis of means (not assuming equal variances)

data:  karma and flairCat
F = 461.99, num df = 7.0, denom df = 1549.5, p-value < 2.2e-16