Identifying crash-prone locations with quantile regression.

Identifying locations that exhibit the greatest potential for safety improvements is becoming more and more important because of competing needs and a tightening safety improvement budget. Current crash modeling practices mainly target changes at the mean level. However, crash data often have skewed distributions and exhibit substantial heterogeneity. Changes at mean level do not adequately represent patterns present in the data. This study employs a regression technique known as the quantile regression. Quantile regression offers the flexibility of estimating trends at different quantiles. It is particularly useful for summarizing data with heterogeneity. Here, we consider its application for identifying intersections with severe safety issues. Several classic approaches for determining risk-prone intersections are also compared. Our findings suggest that relative to other methods, quantile regression yields a sensible and much more refined subset of risk-prone locations.

[1]  G R Wood.  Confidence and prediction intervals for generalised linear accident models. , 2005, Accident; analysis and prevention.

[2]  Michael Rosholm,et al.  The public-private sector wage gap in Zambia in the 1990s: A quantile regression approach , 2001 .

[3]  Fred L Mannering,et al.  A note on modeling vehicle accident frequencies with random-parameters count models. , 2009, Accident; analysis and prevention.

[4]  Jeng-Min Chiou,et al.  Quasi-Likelihood Regression with Unknown Link and Variance Functions , 1998 .

[5]  L E Haefner,et al.  METHODS FOR EVALUATING HIGHWAY SAFETY IMPROVEMENTS , 1975 .

[6]  John A. Nelder,et al.  Likelihood, Quasi-likelihood and Pseudolikelihood: Some Comparisons , 1992 .

[7]  R. Koenker,et al.  Regression Quantiles , 2007 .

[8]  J. Losilla,et al.  Overdispersion in the Poisson Regression Model , 2007 .

[9]  José A.F. Machado,et al.  Quantiles for Counts , 2002 .

[10]  Douglas W Harwood,et al.  Strategic Intersection Safety Program Guide , 2009 .

[11]  Paul Hewson.  Quantile regression provides a fuller analysis of speed data. , 2008, Accident; analysis and prevention.

[12]  James W. Taylor.  A Quantile Regression Approach to Estimating the Distribution of Multiperiod Returns , 1999 .

[13]  Tarek Sayed,et al.  Accident prediction models with random corridor parameters. , 2009, Accident; analysis and prevention.

[14]  Srinivas R. Geedipally,et al.  Effects of Varying Dispersion Parameter of Poisson–Gamma Models on Estimation of Confidence Intervals of Crash Prediction Models , 2008 .

[15]  Colin Lin,et al.  Paper 213-30 an Introduction to Quantile Regression and the Quantreg Procedure , 2005 .

[16]  José A.F. Machado,et al.  Earning functions in Portugal 1982–1994: Evidence from quantile regressions , 2001 .

[17]  Kevin F. Hallock,et al.  Individual heterogeneity in the returns to schooling: instrumental variables quantile regression using twins data , 1999 .

[18]  Dominique Lord,et al.  Methodology for estimating the variance and confidence intervals for the estimate of the product of baseline models and AMFs. , 2008, Accident; analysis and prevention.

[19]  J. S. Silva,et al.  Quantiles for Counts , 2002 .

[20]  Dominique Lord,et al.  Effects of Sample Size on Goodness-of-Fit Statistic and Confidence Intervals of Crash Prediction Models Subjected to Low Sample Mean Values , 2006 .

[21]  Jeffrey C Murray,et al.  Quantile effects of prenatal care utilization on birth weight in Argentina. , 2009, Health economics.

[22]  R. Winkelmann.  Reforming health care: evidence from quantile regressions for counts. , 2006, Journal of health economics.