Performance model is one of the key elements in transportation infrastructure management systems. Both observed and unobserved difference among the sections (helerogeneities) should be accounted for in modeling the performance. The observed heterogeneity is addressed through explanatory variables; while the unobserved heterogeneity results from other factors not included in the explanatory variables. Most of the existing work only focuses on the observed heterogeneity. Thus, the uncertainty on performance modeling is not well captured. In this paper, the issue on performance heterogeneity is investigated. A structured econometric model with hierarchical parameter structure is established. The Maximum Simulated Likelihood approach is applied to estimate the model. It is found through statistical analysis and test that unobserved heterogeneity is significant. In addition to the population parameter estimates, the individual-specific parameter estimates are also obtained, which are helpful in revealing the deterioration behavior of individual sections.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Incorporating Unobserved Heterogeneity in Pavement Deterioration Modeling


    Contributors:

    Conference:

    Ninth International Conference on Applications of Advanced Technology in Transportation (AATT) ; 2006 ; Chicago, Illinois, United States



    Publication date :

    2006-08-04




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Incorporating Unobserved Heterogeneity in Pavement Deterioration Modeling

    Hong, F. / Prozzi, J. A. / American Society of Civil Engineers | British Library Conference Proceedings | 2005




    Development of Safety Performance Functions: Incorporating Unobserved Heterogeneity and Functional Form Analysis

    Wali, Behram / Khattak, Asad J. / Waters, Jim et al. | Transportation Research Record | 2018