Incorporating aleatory and epistemic uncertainties in the modelling of construction duration

Purpose

This study aims to develop a model which incorporates the impact of both aleatory and epistemic uncertainties into construction duration predictions, in a manner that is consistent with the nature/quality of information available about various factors which bring about uncertainties.

Design/methodology/approach

Data relating to 178 completed Tertiary Education Trust Fund (TETfund) building construction projects were obtained from construction firms via questionnaire survey. Using 90% of the data, the model was developed in the form of a hybrid-based algorithm implemented through a suitable user-friendly graphical user interface (GUI) using MATLAB programming language. Bayesian model averaging, Monte Carlo simulation and fuzzy logic were the statistical methods used for the algorithm development, prior to its GUI implementation in MATLAB. Using the remaining 10% data, the model's predictive accuracy was assessed via the independent samplest-test and the mean absolute percentage error (MAPE).

Findings

The developed model's predictions were found not statistically different from those of actual duration estimates in the 10% test data, with a MAPE of just 2%. This suggests that the model's ability to incorporate both aleatory and epistemic uncertainties improves accuracy of duration predictions made using it.

Research limitations/implications

The model was developed using a particular type of building projects (TETfund building construction projects), and so its use is limited to projects with characteristics similar to those used for its development.

Practical implications

The developed model's predictions are expected to serve as a useful basis for consultancy firms and contractor organisations to make more realistic schedules and benchmark measures of construction period, thereby facilitating effective planning and successful execution of construction projects.

Originality/value

The study presented a model which permits combined manipulation of aleatory and epistemic uncertainties, hence ensuring a more realistic incorporation of uncertainty into construction duration predictions.