Abstract
We consider a model, within a Bayesian framework, which can be used to predict the number of accidents occurring at a road junction in a given period of time. The predictions are based on measurements of the traffic flows as well as on covariates which describe important features of the junctions. Various approximate and estimative methods, which use Gibbs sampling, posterior normality and Laplace approximations, are considered and compared. Procedures to assess the importance of the different covariates through the use of the Kullback-Leibler measure of divergence are also developed.
Similar content being viewed by others
References
Aitchison, J. (1975). Goodness of prediction fit.Biometrika, 62:547–554.
Barnett, V. andWright, D. (1992). Biomedical applications for a generalized linear functional Poisson model.J. Appl. Statist., 19:41–47.
Bernardo, J. andSmith, A. (1994).Bayesian Theory. Wiley, Chichester.
Dunsmore, I. andRobson, D. (1997). Prediction in some poisson errors in variables models.Scand. J. Statist., 24:543–554.
Gaver, D. andO'Muircheartaigh, I. (1987). Robust empirical Bayes analyses of event rates.Technometrics, 29:1–15.
Gelfand, A. andSmith, A. (1990). Sampling-based approaches to calculating marginal densities.J. Amer. Statist. Ass., 85:398–409.
Gilks, W. andWild, P. (1992). Adaptive rejection sampling for Gibbs sampling.Appl. Statist., 41:337–348.
Kullback, S. andLeibler, R. (1981). On information and sufficiency.Ann. Math. Statist., 22:79–86.
Magalhães, F. (1997).Prediction in Poisson and other errors in variables models. Ph.D. thesis, University of Sheffield.
O'Hagan, A. (1994).Bayesian Inference-Kendalla's Advanced Theory of Statistics, vol. 2B. Edward Arnold, London.
Wright, D. andBarnett, V. (1991). Fitting predictive accident models in GLIM with uncertainty in the flow estimates. Transport and Road Research Laboratory Report CR286, Department of Transport, UK.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Magalhães, F., Dunsmore, I.R. Predicting the number of accidents at a road junction. Test 12, 153–172 (2003). https://doi.org/10.1007/BF02595817
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02595817
Key words
- Bayesian prediction
- covariate selection
- Gibbs sampling
- Kullback-Leibler divergence
- Laplace appriximation
- Poisson errors in variables models
- posterior normality
- predictive distributions