A Comparison of Activity Time Estimates Methods in PERT

DOI: 10.14416/j.ind.tech.2022.12.005


  • Nanthawat Maha Department of Mathematics, Faculty of Science, Naresuan University
  • Kanlaya Boonlha Department of Mathematics, Faculty of Science, Naresuan University


Critical activity, The activity mean, The activity variance, PERT


The objective of this research was to study and compare methods for estimating the mean and variance of activity time with 7 approximation techniques, including the Program Evaluation and Review Technique (PERT) approximation method, the Normal distribution approximation method, the Lognormal distribution approximation method, the modified PERT approximation method, the Ginzburg's approximation method, the Shankar and Sireesha approximation method and the Weibull distribution approximation method. The criterion for comparison is the percentage error in estimating the mean and variance of activity time. The number of critical activities used in the study was 5, 10, 20, ..., 90, and 100 activities. The simulations were performed with the Monte Carlo technique 1,000 times for each situation. The results of this research showed that all approximation methods had the same critical activity. The modified PERT approximation method was the lowest percentage error in estimating the mean and variance of activity time and then decreases as the number of critical activities increased. Considering all methods, the modified PERT approximation method is the most appropriate for the data and situation studied.


Download data is not yet available.


K. Vanichbuncha, Quantitative analysis, 1st Ed., Faculty of commerce and accountancy, Chulalongkorn University, Bangkok, Thailand, 2010. (in Thai)

P. Lalitaporn, Critical path national geographic national method and PERT program evaluation and review technique, 5th Ed., Technology Promotion Association (Thailand-Japan), Bangkok, Thailand, 1998. (in Thai)

I.M. Premachandra, An approximation of the activity duration distribution in PERT, Computers and Operations Research, 2001, 28(5), 443-452.

N.R. Shankar and V. Sireesha, An approximation for the activity duration distribution supporting original PERT, Applied Mathematical Sciences, 2009, 3(57), 2823-2834.

E.L. McCombs, M.E. Elam and D.B. Pratt Estimating task duration in PERT using the weibull probability distribution, Journal of Modern Applied Statistical Methods, 2009, 8(1), 282-288.

J. Fente, C. Schexnayder and K. Knutson, Defining a probability distribution function for construction simulation, Journal of Construction Engineering and Management, 2000, 126(3), 234-241.

V. Sireesha and N.R. Shankar, Analysis of time estimates on right skewed distribution of activity times in PERT, Journal of Statistics and Mathematics, 2011, 2(1), 15-22.

S. Mohan, M. Gopalakrishnan, H. Balasubramanian and A. Chandrashekar, A lognormal approximation of activity duration in PERT using two time estimates, Journal of the Operational Research Society, 2007, 58(6), 827-831.

B. Nadondu and N. Sriputtha, Study on cleanroom construction project by applying the techniques of program evaluation and review (PERT)/critical path method (CPM): A case study of automotive assembly plant, The 5th Rajamangala Manufacturing and Management Technology Conference 2020 (RMTC 2020), Proceeding, 2020, 227-233 (in Thai)

D.G. Malcolm, J.H. Roseboom, C.E. Clark and W. Fazar, Application of a technique for research and development program evaluation, Operations Research, 1959, 7(5), 646-669.

D. Vose, Risk analysis - A quantitative guide, 2nd Ed., John Wiley and Sons, Chichester, US, 2000.

W.D. Cottrell, Simplified program evaluation and review technique (PERT), Journal of Construction Engineering and Management, 1999, 15(1), 16-22.

D.G. Ginzburg, On the distribution of activity time in PERT, Journal of the Operational Research Society, 1988, 39(8), 767–771.

P. Buchsbaum, Modified pert simulation, http://greatsolutions.com.br/images/betaeng.pdf (Accessed on 16 December 2022)






บทความวิจัย (Research article)