A general method for the simulation of observations of a continuous random variable X.
Let u be a pseudo-random number in the interval (0, 1) and let F be the distribution function of X. Then x, given by
is a random observation of X. For example, an exponential random variable X, with mean μ, has distribution function (1−e−x/μ); hence −μln(1−u) is an observation of X.