Reliability of the Box–Jenkins model for forecasting construction demand covering times of economic austerity

Abstract

As a driving engine for growth, the construction industry plays an important role in a country’s economic development process. Despite that, the industry is vulnerable to cyclical oscillation and at times more fundamental changes in work volume when the regional or global economy is hit by unforeseen events. In order to formulate appropriate policies and directions to help ease the impact of a fluctuating volume of construction work, a model that can reliably predict the work of various construction sectors after any economic turbulence would be extremely useful. In this study, the Box–Jenkins approach is used for model development due to its simplicity and sound theoretical background. The results illustrate that the Box–Jenkins models can reliably predict the medium‐term total construction demand and residential demand covering a turbulent period of ups and downs in construction demand. A multiple regression model is also developed to compare against the modelling reliability of the Box–Jenkins model.

Keywords:

• Construction demand
• forecasting
• Box–Jenkins technique
• economic environment

Acknowledgements

The authors are grateful to the Research Grants Council of the Government of Hong Kong Special Administrative Region and The University of Hong Kong for their financial support through the General Research Fund (Grant no.: 7152/07E) and CRCG Seed Funding for Basic Research (Grant no.: 10207434) respectively.