Skip to main content
SpringerLink
Log in

Specification and estimation of a spatially and temporally autocorrelated seemingly unrelated regression model: application to crash rates in China

  • Published:
Transportation Aims and scope Submit manuscript

Abstract

In transportation studies, variables of interest are often influenced by similar factors and have correlated latent terms (errors). In such cases, a seemingly unrelated regression (SUR) model is normally used. However, most studies ignore the potential temporal and spatial autocorrelations across observations, which may lead to inaccurate conclusions. In contrast, the SUR model proposed in this study also considers these correlations, making the model more behaviorally convincing and applicable to circumstances where a three-dimensional correlation exists, across time, space, and equations. An example of crash rates in Chinese cities is used. The results show that incorporation of spatial and temporal effects significantly improves the model. Moreover, investment in transportation infrastructure is estimated to have statistically significant effects on reducing severe crash rates, but with an elasticity of only −0.078. It is also observed that, while vehicle ownership is associated with higher per capita crash rates, elasticities for severe and non-severe crashes are just 0.13 and 0.18, respectively; much lower than one. The techniques illustrated in this study should contribute to future studies requiring multiple equations in the presence of temporal and spatial effects.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Notes

  1. A crash rate per unit VMT is meaningful in certain respects (primarily in cases where one is interested in roadway design and transport policy impacts on safety levels, given a particular level of VMT). However, the focus of this study is motorization’s effects on the safety and welfare of the Chinese population. Thus, crash rates or losses per capita are of primary interest.

  2. An incidental parameters problem means that, for a fixed-effects model, when T is small, estimators of the constant terms do not converge, leading to inconsistent estimators of all coefficients. [See Lancaster (2000).]

  3. A more formal translation is as follows: (1) Provincial capitals are capitals of autonomous regions and municipalities directly under the Central Government; (2) Big cities are those specifically designated in the State Plan, (3) Medium cities: are important at the regional level, and (4) Small cities are important at the county-level.

  4. These two control variables are potentially endogenous, since higher crash rates may beget greater spending. However, this issue is beyond the scope of the article, and the methods proposed here are perfectly applicable to many situations.

  5. Of course, a 500% increase in vehicle ownership is well outside the sample data range of values, so the model may not be appropriate for such extrapolation. This case is offered simply as an example.

References

  • Aarts, L., Schagen, I.: Driving speed and the risk of road crashes: A review. Accident Anal. Prev. 38(2), 215–24 (2006)

    Article  Google Scholar 

  • Anselin, L.: A test for spatial auto-correlation in seemingly unrelated regressions. Econ. Lett. 28(4), 335–41(1988)

    Article  Google Scholar 

  • Anselin, L.: Spatial Econometrics. http://www.csiss.org/learning_resources/content/papers/baltchap.pdf. Cited 10 May 2006 (1999)

  • Blincoe, L., Seay, A., Zaloshnja, E., Miller, T., Romano, E., Luchter, S., Sicer, R.: The economic impact of motor vehicle crashes, 2000. U.S. Department of Transportation, National Highway Traffic Safety Administration, Washington, DC (2002)

    Google Scholar 

  • China Transportation Accident Online (CTAO): Transportation accident prevention and solutions. http://www.122cn.com/read_web.asp?ArticleID=1252.htm. Accessed 10 December 2006 (2005)

  • Cliff, A., Ord, J.K.: Testing for spatial autocorrelation among regrerssion residuals. Geogr. Anal. 4, 267–84 (1972)

    Article  Google Scholar 

  • Egger, P., Pfaffermayr, M.: Distance, trade and FDI: A Hausman-Taylor SUR approach. J. Appl. Econ. 19(2), 227–46 (2004)

    Article  Google Scholar 

  • Elhorst, J.P.: Specification and estimation of spatial panel data models. Int. Reg. Sci. Rev. 26(3), 244–68 (2003)

    Article  Google Scholar 

  • Federal Highway Administration (FHWA).: http://www.fhwa.dot.gov/policy/ohpi/hss/hsspubs.htm. Cited 5 May 2006 (2004)

  • Greene, W.H.: Econometric Analysis 5th edn., Prentice Hall, Upper Saddle River, New Jersy (2002)

    Google Scholar 

  • Ivan, J.N.: New approach for including traffic volumes in crash rate analysis and forecasting. Trans. Res. Rec. 1897, 134–41 (2004)

    Article  Google Scholar 

  • Jin, L.: Value of life: No need to avoid the assessment. Chongqing Environ. Sci. 4, 47–52 (1999)

    Google Scholar 

  • Kapoor, M., Kelejian, H.H., Prucha, I.R.: Panel data models with spatially correlated error components. http://www.isb.edu/faculty/Working_Papers_pdfs/Panel_Data_Models.pdf. Cited 10 May 2006 (2004)

  • Kim, E., Hewings, J.D.G., Hong, C.: An application of an integrated transport network-multiregional CGE model: A framework for the economic analysis of highway projects. Econ. Syst. Res. 16(3), 235–258 (2004)

    Article  Google Scholar 

  • Kweon, Y.J., Kockelman K.M.: Safety effects of speed limit changes: Use of panel models, including speed, use, and design variables. Trans. Res. Rec. 1908, 148–158 (2005)

    Article  Google Scholar 

  • Lancaster, T.: The incidental parameters problem since 1948. J. Econ. 95 (2), 391–414 (2000)

    Google Scholar 

  • Lord, D., Manar, A., Vizioli, A.: Modeling crash-flow-density and crash-flow-V/C ratio relationships for rural and urban freeway segments. Accident Anal. Prev. 37(1), 185–199 (2005)

    Article  Google Scholar 

  • Magnus, J.R.: Multivariate error-components analysis of linear and non-linear regression-models by maximum-likelihood. J. Econ. 19(2–3), 239–285 (1982)

    Google Scholar 

  • Ministry of Public Security of the People’s Republic of China. (MPS): Notice on revised classification of traffic accidents. http://www.szlaw.org/2004/6-14/16749.htm. Cited 10 May 2006 (1991)

  • Noland, R.B.: Relationships between highway capacity and induced vehicle travel. Trans. Res. 35A(1), 47–72 (2001)

    Google Scholar 

  • Noland, R.B., Karlaftis, M.G.: Sensitivity of crash models to alternative specifications. Trans. Res. 41E(5), 439–58 (2005)

    Google Scholar 

  • Persaud, B.N., Retting, R.A., Lyon, C.A.: Crash reduction following installation of centerline rumble strips on rural two-lane roads. Accident Anal. Prev. 36(6), 1073–1079 (2004)

    Article  Google Scholar 

  • Qin, L., Shao, C., Wang, Y.: Analysis of freeway traffic accidents in China. Proce. Conference Traffic Trans. Stud. ICTTS 4, 165–172 (2004)

    Google Scholar 

  • Replogle, M.: Non-motorized vehicles in Asia: Lessons for sustainable transport planning and policy. http://www.environmentaldefense.org/documents/2293_NonmotorizedVehicles Asia. pdf. Cited 11 November 2006 (1991)

  • Schipper, L., Ng, W.S.: Rapid motorization in China: Environmental and social challenges. World Resources Institute, EMBARQ, ADB-JBIC-World Bank East Asia and Pacific Infrastructure Flagship Study (2004)

  • Srinivasan, S., Kockelman, K.: The impacts of bypasses on small- and medium-sized communities: An econometric analysis. J. Trans. Stat. 5(2), 57–69 (2002)

    Google Scholar 

  • Su, J.: Status analysis and countermeasures of road traffic safety in China. Paper presented at International Road Safety Seminar, Beijing, China,18–20 October, (2005)

  • Washington, S., Metarko, J., Fomunung, I., Ross, R., Julian, F., Moran, E.: An inter-regional comparison: Fatal crashes in the southeastern and non-southeastern United States: Preliminary findings. Accident Anal. Prev. 31(1–2), 135–146 (1998)

    Google Scholar 

  • Yi, P., Ran, B.: Streamlining Chinese highway accident data acquisition, communications, and analysis. Trans. Res. Rec. 1846, 31–8 (2003)

    Article  Google Scholar 

  • Zellner, A.: An efficient method of estimating seemingly unrelated regression equations and tests for aggregation bias. J. Am. Stat. Assoc. 57, 348–68 (1962)

    Article  Google Scholar 

  • Zhai, Z.: Cities’ security problem in China and its solving method Paper presented at International Road Safety Seminar, Beijing, China, 18–20 October, (2005)

Download references

Acknowledgments

The Benjamin H. Stevens Graduate Fellowship in Regional Science provided financial support for this study. The authors are grateful for the Institute of Transportation Engineering at Tsinghua University’s provision of data sets. Dr. Huapu Lu was generous in sharing data and resolving data issues. The authors also thank Annette Perrone for her administrative and editing assistance.

Author information

Authors and Affiliations

  1. Department of Civil, Architectural and Environmental Engineering, The University of Texas at Austin, 6.9 ECJ, Austin, TX, 78712-1076, USA

    Xiaokun Wang & Kara M. Kockelman

Authors
  1. Xiaokun Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kara M. Kockelman
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kara M. Kockelman.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Wang, X., Kockelman, K.M. Specification and estimation of a spatially and temporally autocorrelated seemingly unrelated regression model: application to crash rates in China. Transportation 34, 281–300 (2007). https://doi.org/10.1007/s11116-007-9117-9

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11116-007-9117-9

Keywords

Search

Navigation