Since is given as a function of the parameters only in the
form of a differential equation, it is necessary to integrate to
evaluate for any set of parameters 
. This
cannot be done analytically, and so numerical techniques are used.
The method employed is adaptive stepsize fourth order
Runge-Kutta. The algorithm comes directly from the work of Press
et. al. [40].
The method was chosen to give a reasonable amount of accuracy, and a reasonable amount of speed. This algorithm, together with the sampling algorithms discussed were programmed in the C programming language. A number of difficulties arose during the course of the programming and were solved by reference to numerical analysis techniques.