Forecasting construction tender price index inm Hong Kong using vector error correction model

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

45 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)1255-1268
Journal / PublicationConstruction Management and Economics
Volume28
Issue number12
Publication statusPublished - Dec 2010
Externally publishedYes

Abstract

Reliable short- to medium-term prediction of the tender price index (TPI) is crucial to construction stakeholders, and this has stimulated the interest of the research community to seek a more analytical method for TPI forecast. The purpose of this study is to establish an econometric model for accurately predicting the tender price movements based on a group of associated financial and macroeconomic variables. Applying Johansen's method for multivariate cointegration analysis, the tender price was found to be cointegrated with the gross domestic product, construction output and building cost. A vector error correction (VEC) model imposing the cointegration restriction was then developed for the purpose of forecasting. The model was verified against various diagnostic statistical criteria and compared with the Box-Jenkins and regression models. With a mean absolute percentage error for a three-year ahead forecast at 2.9% level, the developed VEC model outperforms the Box-Jenkins and regression models, and is proven to be efficient and reliable in forecasting the short- to medium-term tender price movements. The model can assist estimators to predict the TPI pattern in advance, and it can also help the public sector in planning for the construction workload to improve the stability of the construction market. Although the VEC model developed focuses on the Hong Kong construction market, the econometric technique can be applied to modelling other economic variables. © 2010 Taylor & Francis.

Research Area(s)

  • Cost estimate, Econometric modelling, Forecast, Tender price index, Vector error correction model

Bibliographic Note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to lbscholars@cityu.edu.hk.