### Abstract

Accident count data have often been shown to have overdispersion. On the other hand, the data might contain zero count (excess zeros). The simulation study was conducted to create a scenarios which an accident happen in T-junction with the assumption the dependent variables of generated data follows certain distribution namely Poisson and negative binomial distribution with different sample size of n=30 to n=500. The study objective was accomplished by fitting Poisson regression, negative binomial regression and Hurdle negative binomial model to the simulated data. The model validation was compared and the simulation result shows for each different sample size, not all model fit the data nicely even though the data generated from its own distribution especially when the sample size is larger. Furthermore, the larger sample size indicates that more zeros accident count in the dataset.

Original language | English |
---|---|

Title of host publication | 2016 UKM FST Postgraduate Colloquium: Proceedings of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology 2016 Postgraduate Colloquium |

Publisher | American Institute of Physics Inc. |

Volume | 1784 |

ISBN (Electronic) | 9780735414464 |

DOIs | |

Publication status | Published - 17 Nov 2016 |

Event | 2016 Postgraduate Colloquium of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology, UKM FST 2016 - Selangor, Malaysia Duration: 13 Apr 2016 → 14 Apr 2016 |

### Other

Other | 2016 Postgraduate Colloquium of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology, UKM FST 2016 |
---|---|

Country | Malaysia |

City | Selangor |

Period | 13/4/16 → 14/4/16 |

### Fingerprint

### Keywords

- Hurdle negative binomial
- negative binomial
- Poisson
- Road accident
- simulation study

### ASJC Scopus subject areas

- Physics and Astronomy(all)

### Cite this

*2016 UKM FST Postgraduate Colloquium: Proceedings of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology 2016 Postgraduate Colloquium*(Vol. 1784). [050009] American Institute of Physics Inc.. https://doi.org/10.1063/1.4966828

**Simulation on Poisson and negative binomial models of count road accident modeling.** / Sapuan, M. S.; Razali, Ahmad Mahir; Zamzuri, Zamira Hasanah; Ibrahim, Kamarulzaman.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*2016 UKM FST Postgraduate Colloquium: Proceedings of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology 2016 Postgraduate Colloquium.*vol. 1784, 050009, American Institute of Physics Inc., 2016 Postgraduate Colloquium of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology, UKM FST 2016, Selangor, Malaysia, 13/4/16. https://doi.org/10.1063/1.4966828

}

TY - GEN

T1 - Simulation on Poisson and negative binomial models of count road accident modeling

AU - Sapuan, M. S.

AU - Razali, Ahmad Mahir

AU - Zamzuri, Zamira Hasanah

AU - Ibrahim, Kamarulzaman

PY - 2016/11/17

Y1 - 2016/11/17

N2 - Accident count data have often been shown to have overdispersion. On the other hand, the data might contain zero count (excess zeros). The simulation study was conducted to create a scenarios which an accident happen in T-junction with the assumption the dependent variables of generated data follows certain distribution namely Poisson and negative binomial distribution with different sample size of n=30 to n=500. The study objective was accomplished by fitting Poisson regression, negative binomial regression and Hurdle negative binomial model to the simulated data. The model validation was compared and the simulation result shows for each different sample size, not all model fit the data nicely even though the data generated from its own distribution especially when the sample size is larger. Furthermore, the larger sample size indicates that more zeros accident count in the dataset.

AB - Accident count data have often been shown to have overdispersion. On the other hand, the data might contain zero count (excess zeros). The simulation study was conducted to create a scenarios which an accident happen in T-junction with the assumption the dependent variables of generated data follows certain distribution namely Poisson and negative binomial distribution with different sample size of n=30 to n=500. The study objective was accomplished by fitting Poisson regression, negative binomial regression and Hurdle negative binomial model to the simulated data. The model validation was compared and the simulation result shows for each different sample size, not all model fit the data nicely even though the data generated from its own distribution especially when the sample size is larger. Furthermore, the larger sample size indicates that more zeros accident count in the dataset.

KW - Hurdle negative binomial

KW - negative binomial

KW - Poisson

KW - Road accident

KW - simulation study

UR - http://www.scopus.com/inward/record.url?scp=85014668501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014668501&partnerID=8YFLogxK

U2 - 10.1063/1.4966828

DO - 10.1063/1.4966828

M3 - Conference contribution

VL - 1784

BT - 2016 UKM FST Postgraduate Colloquium: Proceedings of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology 2016 Postgraduate Colloquium

PB - American Institute of Physics Inc.

ER -