No power law distribution?

[Zireael07]

Or should I just use lognormal instead, since the only difference seems to be the length of the tail?

[cgarling]

Might the Pareto or GeneralizedPareto distributions do what you need?

I recently used the Pareto distribution to implement a power-law distribution in a form that is more typical in my domain; it sounds like you probably want to do something similar.

This Wikipedia entry might also be of help.