Although several decades of study have revealed the ubiquity of variat
ion of evolutionary rates among sites, reliable methods for studying r
ate variation were not developed until very recently. Early methods fi
t theoretical distributions to the numbers of changes at sites inferre
d by parsimony and substantially underestimate the rate variation. Rec
ent analyses show that failure to account for rate variation can have
drastic effects, leading to biased dating of speciation events, biased
estimation of the transition:transversion rate ratio, and incorrect r
econstruction of phylogenies.