Determining the probability of project cost overruns

Peter E.D. Love, Xiangyu Wang, Chun Pong Sing, Robert L.K. Tiong

Research output: Journal article publicationJournal articleAcademic researchpeer-review

105 Citations (Scopus)


The statistical characteristics of cost overruns experienced from contract award in 276 Australian construction and engineering projects were analyzed. The skewness and kurtosis values of the cost overruns are computed to determine if the empirical distribution of the data follows a normal distribution. The Kolmogorov-Smirnov, Anderson-Darling, and chi-squared nonparametric tests are used to determine the goodness of fit of the selected probability distributions. A three-parameter Frechet probability function is found to describe the behavior of cost overruns and provide the best overall distribution fit. The Frechet distribution is then used to calculate the probability of a cost overrun being experienced. The statistical characteristics of contract size and cost overruns were also analyzed. The Cauchy (<A$1 million), Wakeby (A$1 to 10 million, <A$101 million) and four-parameter Burr (A$11 to 50 million) tests were found to provide the best distribution fits and used to calculate cost overrun probabilities by contract size. Ascertaining the best fit probability distribution from an empirical distribution at contract award can produce realistic probabilities of cost overruns, which should then be incorporated into a construction cost contingency.
Original languageEnglish
Pages (from-to)321-330
Number of pages10
JournalJournal of Construction Engineering and Management
Issue number3
Publication statusPublished - 1 Mar 2013
Externally publishedYes


  • Australia
  • Cost overrun
  • Distribution fitting
  • Probability
  • Probability distribution

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Industrial relations
  • Strategy and Management


Dive into the research topics of 'Determining the probability of project cost overruns'. Together they form a unique fingerprint.

Cite this