Forecasting project progress and early warning of project overruns with probabilistic methods

Forecasting is a critical component of project management. Project managers must beable to make reliable predictions about the final duration and cost of projects startingfrom project inception. Such predictions need to be revised and compared with theproject's objectives to obtain early warnings against potential problems. Therefore, theeffectiveness of project controls relies on the capability of project managers to makereliable forecasts in a timely manner.This dissertation focuses on forecasting project schedule progress withprobabilistic methods. Currently available methods, for example, the critical pathmethod (CPM) and earned value management (EVM) are deterministic and fail toaccount for the inherent uncertainty in forecasting and project performance.The objective of this dissertation is to improve the predictive capabilities ofproject managers by developing probabilistic forecasting methods that integrate allrelevant information and uncertainties into consistent forecasts in a mathematicallysound procedure usable in practice. In this dissertation, two probabilistic methods, the Kalman filter forecasting method (KFFM) and the Bayesian adaptive forecasting method(BAFM), were developed. The KFFM and the BAFM have the following advantagesover the conventional methods: (1) They are probabilistic methods that provideprediction bounds on predictions; (2) They are integrative methods that make better useof the prior performance information available from standard construction managementpractices and theories; and (3) They provide a systematic way of incorporatingmeasurement errors into forecasting.The accuracy and early warning capacity of the KFFM and the BAFM were alsoevaluated and compared against the CPM and a state-of-the-art EVM scheduleforecasting method. Major conclusions from this research are: (1) The state-of-the-artEVM schedule forecasting method can be used to obtain reliable warnings only after theproject performance has stabilized; (2) The CPM is not capable of providing earlywarnings due to its retrospective nature; (3) The KFFM and the BAFM can and shouldbe used to forecast progress and to obtain reliable early warnings of all projects; and (4)The early warning capacity of forecasting methods should be evaluated and compared interms of the timeliness and reliability of warning in the context of formal early warningsystems.