Turner-Fairbank Highway Research Center

« back to the list

Effects of Varying Dispersion Parameter of Poisson-Gamma Models on Estimation of Confidence Interval

Product Type

Journal Article


Geedipally, S.R. and D. Lord



Full citation

Geedipally, S.R. and D. Lord. Effects of Varying Dispersion Parameter of Poisson-Gamma Models on Estimation of Confidence Intervals of Crash Prediction Models. In Transportation Research Record: Journal of the Transportation Research Board, No. 2061, Transportation Research Board, National Research Council, Washington, D.C., 2008, pp. 46-54.


In estimating safety performance, the most common probabilistic structures of the popular statistical models used by transportation safety analysts for modeling motor vehicle crashes are the traditional Poisson and Poissongamma (or negative binomial) distributions. Because crash data often exhibit overdispersion, Poissongamma models are usually the preferred model. The dispersion parameter of Poissongamma models had been assumed to be fixed, but recent research in highway safety has shown that the parameter can potentially be dependent on the covariates, especially for flow-only models. Given that the dispersion parameter is a key variable for computing confidence intervals, there is reason to believe that a varying dispersion parameter could affect the computation of confidence intervals compared with confidence intervals produced from Poissongamma models with a fixed dispersion parameter. This study evaluates whether the varying dispersion parameter affects the computation of the confidence intervals for the gamma mean (m) and predicted response (y) on sites that have not been used for estimating the predictive model. To accomplish that objective, predictive models with fixed and varying dispersion parameters were estimated by using data collected in California at 537 three-leg rural unsignalized intersections. The study shows that models developed with a varying dispersion parameter greatly influence the confidence intervals of the gamma mean and predictive response. More specifically, models with a varying dispersion parameter usually produce smaller confidence intervals, and hence more precise estimates, than models with a fixed dispersion parameter, both for the gamma mean and for the predicted response. Therefore, it is recommended to develop models with a varying dispersion whenever possible, especially if they are used for screening purposes.

Available From

Transportation Research Board

Link To Journal Article

Effects of Varying Dispersion Parameter of Poisson-Gamma Models on Estimation of Confidence Interval


Confidence intervals
Mathematical models
Mathematical prediction
Negative binomial distributions
Poisson distributions
Regression analysis
Rural areas
Three leg intersec

« Back to the List

HSIS Summaries

HSIS Summary Reports are two to eight pages in length and include a brief description of the issue addressed, data used, methodology applied, significant results, and practical implications.

Read More

Research Reports

A variety of research studies have been performed using data from HSIS. Many of the final reports prepared are now available electronically.

Read More

Technical Summaries

Research reports are often summarized in executive summaries, technical briefs, or other abbreviated formats. Included here are those road safety summaries that involved research using HSIS data.

Read More

Safety Analysis Tools

In addition to conducting research, HSIS resources are also used to develop products that can be used by practitioners in the analysis of safety problems.

Read More

Other Projects

HSIS data are sometimes used in research studies that result in other types of finished products, such as dissertations, theses, and conference proceedings.

Read More