... differ.¹

When I introduced nucleotide diversity before, I defined $\delta_{ij}$ as the number of nucleotides that differ between haplotypes $i$ and $j$. It's a little easier for what follows if we think of it as the fraction of nucleotides at which they differ instead.

.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.

... components.²

As with $F$-statistics, the actual estimation procedure is more complicated than I describe here. Standard approaches to AMOVA use method of moments calculations analogous to those introduced by Weir and Cockerham for $F$-statistics [4]. Bayesian approaches are possible, but they are not yet widely available.

.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.

... error.³

There wouldn't be any rounding error if we had access to the raw data.

.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.

... recall,⁴

Look back at http://darwin.eeb.uconn.edu/eeb348/lecture-notes/coalescent/node6.html for the details.

.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.