Explaining Heterogeneity in Pavement Deterioration: Clusterwise Linear Regression Model
Publication: Journal of Infrastructure Systems
Volume 20, Issue 2
Abstract
A clusterwise linear regression model of pavement deterioration is presented. The model provides a framework to simultaneously segment a population and to describe performance with a set of regression models, one for each segment. Instead of relying on observed criteria, the objective in the segmentation is to maximize within-segment variation explained by a set of commonly specified regression models. To illustrate the methodology, performance models were estimated for a panel of 131 pavements from the American Association of State Highway Officials (AASHO) road test. Pavements in different segments display systematic but unobserved differences in their responses, i.e., unobserved heterogeneity, which manifests itself in segment-level coefficients that differ in their magnitude and sign. This is radically different than other approaches in the literature that explain such differences with individual-level error/intercept terms, but that rely on the assumption of constant and homogeneous coefficients capturing the effect of explanatory variables across the population. How segment-level effects can be used to support tailored management policies, e.g., maintenance and repair, or setting weight restrictions is discussed. Finally, a rigorous assessment is conducted of the proposed model that includes comparison with a population-level regression model and to a clusterwise model that relies on observed factors from the original experimental design: the loop-lane, i.e., the design-loading, configuration.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
This work was partially supported by grants awarded by the National Science Foundation and by the Infrastructure Technology Institute at Northwestern University to the second author.
References
Archilla, A. (2006). “Repeated measurement data analysis in pavement deterioration modeling.” J. Infrastruct. Syst., 163–173.
Archilla, A., and Madanat, S. (2000). “Development of a pavement rutting model from experimental data.” J. Transp. Eng., 291–299.
Bektas, B., Carriquiry, A., and Smadi, O. (2012). “Using classification trees for predicting national bridge inventory condition ratings.” J. Infrastruct. Syst., 19(4), 425–433.
Brusco, M., Cradit, J., Steinley, D., and Fox, L. (2008). “Cautionary remarks on the use of clusterwise regression.” Multivariate Behav. Res., 43(1), 29–49.
Brusco, M., Cradit, J., and Tashchian, A. (2003). “Multicriterion clusterwise regression for joint segmentation settings: An application to customer value.” J. Mark. Res., 40(2), 225–234.
Burnham, K., and Anderson, D. (2002). Model selection and multi-model inference: A practical information-theoretic approach, 2nd Ed., Springer, New York.
Carnahan, J., Davis, W., Shahin, M., Keane, P., and Wu, M. (1987). “Optimal maintenance decisions for pavement management.” J. Transp. Eng., 113(5), 554–573.
Chu, C., and Durango-Cohen, P. (2008c). “Incorporating maintenance effectiveness in the estimation of dynamic infrastructure performance models.” Comput. Aided Civ. Infrastruct. Eng., 23(3), 174–188.
Chu, C., and Durango-Cohen, P. (2008a). “Empirical comparison of statistical pavement performance models.” J. Infrastruct. Syst., 138–149.
Chu, C., and Durango-Cohen, P. (2008b). “Estimation of dynamic performance models for transportation infrastructure using panel data.” Transp. Res. B Methodol., 42(1), 57–81.
DeSarbo, W., Oliver, R., and Rangaswamy, A. (1989). “A simulated annealing methodology for clusterwise linear regression.” Psychometrika, 54(4), 707–736.
Durango-Cohen, P., and Madanat, S. (2002). “Optimal maintenance and repair policies in infrastructure management under uncertain facility deterioration rates: An adaptive control approach.” Transp. Res. A Policy Pract., 36(9), 763–778.
Gendreau, M., and Soriano, P. (1998). “Airport pavement management systems: An appraisal of existing methodologies.” Transp. Res. A Policy Pract., 32(3), 197–214.
Golabi, K., Kulkarni, R., and Way, G. (1982). “A statewide pavement management system.” Interfaces, 12(6), 5–21.
Greene, W. (2011). Econometric analysis, 7th Ed., Prentice Hall, Upper Saddle River, NJ.
Highway Research Board. (1962). “The AASHO road test.”, National Academy of Science, National Research Council, Washington, DC.
Hong, F., and Prozzi, J. (2006). “Estimation of pavement performance deterioration using Bayesian approach.” J. Infrastruct. Syst., 77–86.
Hong, F., and Prozzi, J. (2010). “Roughness model accounting for heterogeneity based on in-service pavement performance data.” J. Transp. Eng., 205–213.
Hsiao, C. (1986). Analysis of panel data, Cambridge University Press, Cambridge, U.K.
Hudson, W., Haas, R., and Uddin, W. (1997). Infrastructure management, McGraw-Hill, New York.
Humplick, F. (1992). “Highway pavement distress evaluation: Modeling measurement error.” Transp. Res. B Methodol., 26(2), 135–154.
Lau, K., Leung, P., and Tse, K. (1999). “A mathematical programming approach to clusterwise regression model and its extension.” Eur. J. Operat. Res., 116(3), 640–652.
Luo, Z., and Chou, Y. (2006). “Pavement condition prediction using clusterwise regression.” Transportation Research Record 1974, Transportation Research Board, Washington, DC, 70–77.
Luo, Z., and Yin, H. (2008). “Probabilistic analysis of pavement distress ratings with the clusterwise regression method.” Transportation Research Record 2084, Transportation Research Board, Washington, DC, 38–46.
Madanat, S., Karlaftis, M., and McCarthy, P. (1997). “Probabilistic infrastructure deterioration models with panel data.” J. Infrastruct. Syst., 4–9.
McNeil, S., Markow, M., Neumann, L., Ordway, J., and Uzarski, D. (1992). “Emerging issues in transportation facilities management.” J. Transp. Eng., 477–495.
Onar, A., Thomas, F., Choubane, B., and Byron, T. (2006). “Statistical mixed effects models for evaluation and prediction of accelerated pavement testing results.” J. Transp. Eng., 771–780.
Prozzi, J., and Madanat, S. (2003). “Incremental nonlinear model for predicting pavement serviceability.” J. Transp. Eng., 635–641.
Späth, H. (1977). “Computational experience with the exchange method.” Eur. J. Operat. Res., 1(1), 23–31.
Späth, H. (1979). “Algorithm 39: Clusterwise linear regression.” Computing, 22(4), 367–373.
Späth, H. (1982). “Algorithm 48: A fast algorithm for clusterwise linear regression.” Computing, 29(2), 175–181.
Sunitha, V., Veeraragavan, A., Srinivasan, K., and Matthew, S. (2012). “Cluster based pavement deterioration models for low volume rural roads.” ISRN Civ. Eng., Article ID 565948.
Tsai, Y., Kaul, V., and Mersereau, R. (2010). “Critical assessment of pavement distress segmentation methods.” J. Transp. Eng., 11–19.
Van Noortwjk, J., and Frangopol, D. (2004). “Deterioration and maintenance models for insuring safety of civil infrastructures at lowest life-cycle cost.” Life-cycle performance of deteriorating structures: Assessment, design and management, D. Frangopol, E. Brühwiler, M. Faber and B. Adey, eds., ASCE, Reston, VA, 384–391.
Wang, K., and Li, Q. (2010). “Gray clustering-based pavement performance evaluation.” J. Transp. Eng., 38–44.
Washington, S., Karlaftis, M., and Mannering, F. (2003). Statistical and econometric methods for transportation data analysis, Chapman and Hall/CRC, Boca Raton, FL.
Wedel, M., and Kamakura, W. (2000). Market segmentation: Conceptual and methodological foundations, Kluwer Academic, Norwell, MA.
Wedel, M., and SteenKamp, J. (1989). “Fuzzy clusterwise regression approach to benefit segmentation.” Int. J. Res. Mark., 6(4), 241–258.
Yu, J., Chou, E., and Luo, Z. (2007). “Development of linear mixed effects models for predicting individual pavement conditions.” J. Transp. Eng., 347–354.
Information & Authors
Information
Published In
Copyright
© 2014 American Society of Civil Engineers.
History
Received: Oct 19, 2012
Accepted: Aug 1, 2013
Published online: Aug 3, 2013
Published in print: Jun 1, 2014
Discussion open until: Jun 30, 2014
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.