A contribution to stochastic projects analysis by using PERT

PERT (Program Evaluation and Review Technique) is a well-known method for planning and scheduling large-scale stochastic projects with random activity durations. The paper deals with an approximation to probability distribution of this random variable by using beta distribution and triangular distribution. Basic characteristics of the triangular probability distribution are derived and compared with the corresponding characteristics of the beta distribution with the same values of optimistic, pessimistic and most likely estimate of the random variable. Further, results of some probabilistic calculations in stochastic projects are compared, if the beta distribution or the triangular distribution was used for an approximation to the probability distribution of random activity durations. All derived relations are illustrated by a simple concrete example.