An analysis of the use of the Beta Distribution for planning large projects

  1. Lookup NU author(s)
  2. Professor Christian Hicks
  3. Dr Fouzi Hossen
Author(s)Hicks C, Hossen FA
Editor(s)
Publication type Conference Proceedings (inc. Abstract)
Conference NameFifth Annual Meeting of ENBIS
Conference LocationNewcastle upon Tyne
Year of Conference2005
Legacy Date14-16 September 2005
Volume
Pages
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
Large complex engineering projects are usually planned using project management systems that are based upon the Project Evaluation and Review Technique (PERT). This approach uses the Beta distribution to represent uncertainties in the duration of activities. The probability density function for a Beta distribution can be uniform, symmetric or skewed depending upon the parameters used. Planners produce three estimates of activity durations: most likely, optimistic and pessimistic. These estimates are used to configure the parameters of the Beta distribution. In practice, uncertainties are cumulative; for example an assembly process cannot start until the latest component is available. This paper explores the relationship between the planning values used, the Beta distribution parameters and shape. A simulation case study is then presented that is based upon data obtained from a capital company that produced large complex products in low volume. The work evaluates the impact that different types of uncertainty have on manufacturing performance for products with many levels of assembly