Multicanonical Monte Carlo study of a structural phase transition

We present a new method for establishing and exploiting a multicanonical distribution for Monte Carlo sampling across an extended space of macrostates, with particular reference to the study of first-order phase transitions. The method exploits the information contained in measurements of the transition rate between macrostates, in simulations launched from macrostates with low canonical probabilities. We apply the method to the study of the coexistence of two solid phases in a model system of hard spheres with short-range attractive interactions.