The Effects of Different Activity Distributions on Project Duration in PERT Networks

Abstract The original PERT technique assumes β distribution for the activity durations. The developments of the past decades have partly refuted this concept; and many different distributions have been introduced. In our research, various distributions (uniform, triangular, β) are applied in case of closed large-scale infrastructure projects. In this paper, the possible effects of these distributions on the project duration are investigated. It is shown that the use of different distributions with the same three-point estimation has a smaller effect on the project duration than a 10% difference in the values of the three-point estimation.

[1]  James J. Solberg,et al.  The use of cutsets in Monte Carlo analysis of stochastic networks , 1979 .

[2]  Weng-Ming Chu,et al.  A new approximation algorithm for obtaining the probability distribution function for project completion time , 2007, Comput. Math. Appl..

[3]  Charles E. Clark,et al.  Letter to the Editor—The PERT Model for the Distribution of an Activity Time , 1962 .

[4]  Bajis M. Dodin,et al.  Bounding the Project Completion Time Distribution in PERT Networks , 1985, Oper. Res..

[5]  Miklós Hajdu.  Network Scheduling Techniques for Construction Project Management , 1996 .

[6]  Van Slyke,et al.  MONTE CARLO METHODS AND THE PERT PROBLEM , 1963 .

[7]  T. Kotiah,et al.  Another Look at the PERT Assumptions , 1973 .

[8]  Richard M. Van Slyke,et al.  Letter to the Editor---Monte Carlo Methods and the PERT Problem , 1963 .

[9]  Kenneth R. Baker,et al.  Modeling activity times by the Parkinson distribution with a lognormal core: Theory and validation , 2012, Eur. J. Oper. Res..

[10]  Jerzy Kamburowski,et al.  New validations of PERT times , 1997 .

[11]  D. Malcolm,et al.  Application of a Technique for Research and Development Program Evaluation , 1959 .

[12]  Miklós Hajdu.  Effects of the application of activity calendars on the distribution of project duration in PERT networks , 2013 .

[13]  S. Mohan,et al.  A lognormal approximation of activity duration in PERT using two time estimates , 2007, J. Oper. Res. Soc..

[14]  Bajis M. Dodin.  Approximating the distribution functions in stochastic networks , 1985, Comput. Oper. Res..

[15]  Eugene David Hahn,et al.  Mixture densities for project management activity times: A robust approach to PERT , 2008, Eur. J. Oper. Res..

[16]  Jerzy Kamburowski.  Bounding the distribution of project duration in PERT networks , 1992, Oper. Res. Lett..

[17]  Donald L. Fisher,et al.  Stochastic pert networks: OP diagrams, critical paths and the project completion time , 1985, Comput. Oper. Res..

[18]  Vidyadhar G. Kulkarni,et al.  A classified bibliography of research on stochastic PERT networks: 1966-1987 , 1989 .

[19]  David Johnson,et al.  The triangular distribution as a proxy for the beta distribution in risk analysis , 1997 .

[20]  S. Elmaghraby.  Chapter 1 – THE ESTIMATION OF SOME NETWORK PARAMETERS IN THE PERT MODEL OF ACTIVITY NETWORKS: REVIEW AND CRITIQUE , 1989 .

[21]  John M. Burt,et al.  Conditional Monte Carlo: A Simulation Technique for Stochastic Network Analysis , 1971 .