Preliminary Analysis of AASHO Road Test Rigid Pavement Data Using Modern Regression Techniques

Abstract:

The normality assumptions with random errors and constant variance were often violated while analyzing multilevel pavement performance data using conventional regression techniques. Because of its hierarchical data structure, multilevel data are often analyzed using Linear Mixed-Effects (LME) models. The exploratory analysis, statistical modeling, and the examination of model-fit of LME models are more complicated than those of standard multiple regressions. A systematic modeling approach using visual-graphical techniques and LME models was proposed and demonstrated using the original AASHO road test rigid pavement data. The basic modeling approach includes: selecting a preliminary mean structure, selecting a random structure, selecting a residual covariance structure, model reduction, and examining the model fit. A goodness of fit plot indicates that the preliminary LME model provides better explanation to the data.

• Periodical: Advanced Materials Research (Volume 723)
• Pages: 869-876
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.723.869
• Online since: August 2013
• Authors: Hsiang Wei Ker, Ying Haur Lee, T.C. Huang, Ke Lin
• Keywords: AASHO Road Test, Linear Mixed-Effects Models, Modern Regression, Pavement Performance, Prediction Model, Present Serviceability Index, Rigid Pavements

References

[1] H. Goldstein, The Design and Analysis of Longitudinal Studies, New York: Academic Press Inc., 1979.

[2] J.J. Hox, Multilevel analysis of grouped and longitudinal data, in: T.D. Little, K.U. Schnabel, and J. Baumert (Eds.), Modeling Longitudinal and Multilevel Data: Practical Issues, Applied Approaches and Specific Examples, New Jersey: Lawrence Erlbaum Associates, 2000, pp.15-32.

DOI: 10.4324/9781410601940

[3] HRB, The AASHO road test, Report 5, Pavement Research, Special Report 61E. Publication No. 954, Highway Research Board, National Research Council, Washington, D.C., 1962.

[4] H.W. Ker, Application of Regression Spline in Multilevel Longitudinal Modeling, Ph.D. Dissertation, University of Illinois, Urbana, Illinois, 2002.

[5] Y.H. Lee, and H.W. Ker, Reevaluation and Application of the AASHTO Mechanistic-Empirical Pavement Design Guide, Phase I, Summary Report, NSC96-2211-E-032-036, National Science Council, Taiwan, 2008. (In Chinese)

[6] Y.H. Lee, and H.W. Ker, Reevaluation and Application of the AASHTO Mechanistic-Empirical Pavement Design Guide, Phase II, NSC97-2221-E-032-034, Summary Report, National Science Council, Taiwan, 2009. (In Chinese)

[7] H.W. Ker, Linear Mixed Effects Models for Preliminary Analysis of Flexible Pavement Serviceability Index Data, Transportation Research Record 2225, Journal of the Transportation Research Board, Washington, D.C., 2011, pp.32-42.

DOI: 10.3141/2225-05

[8] Y.H. Huang. Pavement Analysis and Design, 2nd ed., Pearson New Jersey: Education, Inc., 2004.

[9] Y.H. Lee, Development of Pavement Prediction Models, Ph.D. Dissertation, University of Illinois, Urbana, Illinois, 1993.

[10] M.R. Banan, and K.D. Hjelmstad, Neural networks and AASHO road test. Journal of Transportation Engineering, ASCE, 122(5), 1996, pp.358-366.

DOI: 10.1061/(asce)0733-947x(1996)122:5(358)

[11] ARA, Inc., Guide for Mechanistic- Empirical Design of New and Rehabilitated Pavement Structure, NCHRP 1-37A Report, Transportation Research Board, National Research Council, Washington, D. C., 2004.

[12] H.W. Ker, Y.H. Lee, and P.H. Wu, Development of fatigue cracking performance prediction models for flexible pavements using LTPP database, Journal of Transportation Engineering, ASCE, 134(11), 2008, pp.477-482.

DOI: 10.1061/(asce)0733-947x(2008)134:11(477)

[13] FHWA, Long-Term Pavement Performance Information Management System: Pavement Performance Database Users Reference Guide, Publication No. FHWA-RD-03-088, Federal Highway Administration, 2004.

[14] J.C. Pinherio, and D.M. Bates, Mixed-Effects Models in S and S-plus, New York: Springer-Verlag, 2000.

[15] R.S. Pindyck, and D.L. Rubinfeld, Econometric Models and Economic Forecasts, 4th ed. New York: McGraw-Hill, Inc., 1998.

[16] C.H. Morrell, J.D. Pearson, and L.J. Brant, Linear transformations of linear mixed-effects models, The American Statistician, 51, 1997, pp.338-343.

DOI: 10.1080/00031305.1997.10474409