Poisson, Poisson-gamma and zero-inflated regression models of motor vehicle crashes: balancing statistical fit and theory.

By D. Lord, S. Washington, J. Ivan. Accident Analysis and Prevention, 2005

924 citations recorded by the source corpus.

Subfields: Automotive Engineering, Control and Systems Engineering, Safety, Risk, Reliability and Quality

View Paper: https://www.semanticscholar.org/paper/35d268a53bb20cf63defcd26be3f6fc80cd2f183

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Control and Systems Engineering

In Safety, Risk, Reliability and Quality

Citations in the corpus

Bayesian Multivariate Poisson Regression for Models of Injury Count, by Severity (2006, neutral): “, Metropolis et al. (1953); Hastings (1970); Tanner and Wong, 1987; Gelfand and Smith, 1990; Smith and Roberts, 1993; Tierney, 1994; and Lee, 2004).”
Quasi-Poisson vs. negative binomial regression: how should we model overdispersed count data? (2007, background): “1 E-mail: jay.verhoef@noaa.gov 2766 the distributions can be found in Joe and Zhu (2005) and Lord et al. (2005).”
Bayesian Multivariate Poisson Lognormal Models for Crash Severity Modeling and Site Ranking (2009, background): “Therefore, crash data often exhibit excess zeroes compared to those expected under a Poisson process (4, 5).”
Modeling over-dispersed crash data with a long tail: Examining the accuracy of the dispersion parameter in Negative Binomial models (2015, background): “Lord et al. (2005) provided a fundamental definition that the over-dispersion arises from the actual nature of the crash process.”
Crash Frequency Analysis with Generalized Additive Models (2008, background): “The most popular statistical models used in crash frequency studies so far are generalized linear models (GLMs), including Poisson (2), Poisson–gamma or negative binomial (NB) (3–5), gamma (6), and zero-inflated models (3, 7, 8).”
Multivariate random parameters zero-inflated negative binomial regression for analyzing urban midblock crashes (2018, methodology): “The zero-inflated models are often adopted for univariate count data with excess zeros (Lambert, 1992; Lord et al., 2005).”
Visualization and analysis of mapping knowledge domain of road safety studies. (2018, methodology): “…severity analysis of road accidents, Models For Count Data are often used for analysis of the contributory factors to crash frequency (Martin, 2002; Lord et al., 2005; Wong et al., 2007); Discrete Outcome Models are often used for analysis of the injury severities in crashes (Kim et al., 2007;…”
Developing a Random Parameters Negative Binomial-Lindley Model to analyze highly over-dispersed crash count data (2018, background): “Lord et al. (2005) pointed out that over-dispersion arises from the actual nature of the crash process.”
Temperature and Flow Effects on Migration Timing of Chinook Salmon Smolts (2009, background): “Both distributions tend to underpredict the occurrence of zero counts relative to the observed data for datasets with a large number of zero counts ( Lord et al. 2005 ; Long and Freese 2006 ) requiring a zero-inflated version (ZINB or ZIP).”
Exploring the application of the negative binomial-generalized exponential model for analyzing traffic crash data with excess zeros (2015, background): “Lord et al. (2005, 2007) and Lord and Geedipally (2011; 2014) provide discussions about the advantages and limitations of these distributions and models.”