Once the fractal dimensions were obtained, several statistical procedures were
conducted. A 2-way ANOVA was run separating the sexes and species which resulted in
four groups. Regressions were also conducted between the fractal dimensions and each
size/shape variable to try to determine if there was a predictable relationship between any
of these variables. The regressions were conducted with only the species separated not
the sexes. Both of these procedures were evaluated for significance based on a P-
value<0.05. The fractal dimension data for the four groups was also bootstrapped to
obtain a more reliable mean since the sample sizes were small. Bootstrapping makes no
assumptions about the distributional properties of the data.