The incidence of road fatality in the world is most alarming. It is noted that the number of deaths in Nigeria by COVID-19 is nothing compared to the deaths by road accidents. As at July 2022 the total number of deaths by COVID-19 is 3,144 while the number of deaths by road accident is 10116, which is about 69% higher than deaths due to COVID-19. This paper hence considered the road accident fatalities during the COVID-19 hit period (2019-2021) in all the states of Nigeria. Due to the count nature of the response variable (Number of deaths) Poisson regression and the negative binomial regression are considered in other to build a model for predicting number of deaths due to road accidents. Both methods were compared to determine the most appropriate. The results of the analysis show that the number of male fatality is more than double that of the female and children with a percentage of 70.6%. The data revealed that Akwa Ibom State and Kaduna State have the minimum and the maximum number of deaths with 47 and 1070 respectively. The Poisson regression and Negative Binomial (NB) regression were considered for analysis. The data showed evidence of over-dispersion rendering the Poisson regression inadequate for the analysis, leaving the negative binomial regression as an alternative. Further assessment of the two models based on the mean-variance relationship, goodness of fit test, AIC and BIC, identified the NB as a better model for the analysis. The model considered the number of people killed as the response variable while the covariates include; speed limit, car issues, dangerous driving, fatigue, street light, bad roads and general factors. Applying the NB regression produced an end result model with only dangerous driving as a significant factor in road accidents fatalities. This shows that dangerous driving is the major cause of deaths on Nigerian roads. The paper also noted that based on the available data, road accidents is a more threatening fatal hazard than COVID-19 with a total death toll of 3,144 for COVID-19 and 10,116 for Road accidents in the same period considered. The paper suggests that the government should put more weight in curbing road accidents by instructing the road safety commission to focus more in developing new strategies or improving on the old strategies for eliminating or reducing dangerous driving by drivers on Nigerian roads.
| Published in | International Journal of Statistical Distributions and Applications (Volume 8, Issue 3) |
| DOI | 10.11648/j.ijsd.20220803.11 |
| Page(s) | 40-46 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2024. Published by Science Publishing Group |
Negative Binomial Regression, Poisson Regression, Over-dispersion, Goodness of Fit, Road Accident Fatalities
| [1] | Alexander K. M., Oscar O. N., Anthony G. W. (2016). Statistical Models for Count Data. Science Journal of Applied Mathematics and Statistics. Vol. 4, No. 6, 2016, pp. 256-262. |
| [2] | Ameratunga S, Hijar M, Norton R. (2006). Road-traffic injuries: Confronting disparities to address a global-health problem. Lancet. 367: 1533–1540. Available. http://www.thelancet.com/journals/lancet/article/PIIS0140-6736(06)68654-6/fulltext |
| [3] | Anraku, K. and Yanagimoto T., (1990). Estimation for the negative binomial distribution based on the conditional likelihood. Comm. Statist. Simul. Comput., 19: 771-786. |
| [4] | Bhaduri E., Manoj B. S., Zia W., Arkopal K. G, Charisma F. C. (2020). Modelling the effects of COVID-19 on travel mode choice be-haviour in India. Transportation Research Interdisciplinary Perspectives; 8. https://doi.org/10.1016/j.trip.2020.100273. |
| [5] | Blackburn, M. L. (2015). The relative performance of Poisson and negative binomial regression estimators. Oxford Bulletin of Economics and Statistics: 77; 605-616. |
| [6] | Cameron A. C. and Trivedi P. K. (1986). Econometric models based on count data. Comparisons and applications of some estimators and tests. Journal of Applied Econometrics, 1: pp 29-53. |
| [7] | Cameron, A. C., & Trivedi, P. K. (2013). Regression analysis of count data, Cambridge university press. |
| [8] | Cannizzaro, F, Greco, G.; Rizzo, S. Sinagra, E. (1978) Result of the measurement carried in order to verify the validity of the Poisson-exponential distribution in radioactive decay event. The international Journal of Applied Radiation and Isotopes; 29 (11): 649. |
| [9] | Favero L. P., Paulo R., Paulo P. B., Hamilton L. C., Paulo M. F. C. (2021). Count Data Regression Analysis: Concepts, Overdispersion Detection, Zero-inflation Identification, and Applications with R. Practical Assessment, Research and Evaluation, 26: 13, 1-22. |
| [10] | Greenwood, M., and Yule, G. U. (1920). An Inquiry into the Nature of Frequency Distributions of Multiple Happenings, with Particular Reference to the Occurrence of Multiple Attacks of Disease or Repeated Accidents. Journal of the Royal Statistical Society A, 83: pp. 255-279. |
| [11] | Gourieroux, C. and A. Monfort (1997), Simulation Based Econometric Methods, Oxford: Oxford University Press. |
| [12] | Hilbe J. M. (2014). Modeling Count Data. Cambridge University Press, pp 126-161. |
| [13] | Inada, H., L. Ashraf and S. Campbell (2021). COVID-19 lockdown and fatal motor vehicle collisions due to speed-related traffic violations in Japan: A time-series study, Injury Pre- vention, Vol 27/1, pp. 98-100, http://dx.doi.org/10.1136/injuryprev-2020- 043947. |
| [14] | Lambert D (1992). “Zero-inflated Poisson Regression, With an Application to Defects in Manufacturing.” Technometrics, 34: pp 1-14. |
| [15] | McCullagh P, Nelder JA (1989). Generalized Linear Models. 2nd edition. Chapman & Hall, London. |
| [16] | Nelder JA, Wedderburn RWM (1972). “Generalized Linear Models.” Journal of the Royal Statistical Society A, 135: 370-384. |
| [17] | Nixon D. C., (1991). Event count Models for Supreme Court dissents. Political Methodology; 4: 11-14. |
| [18] | Osgood, W. (2000). Poisson-based Regression Analysis of Aggregate crime Rates. Journal of Quantitative Criminology; 16: 21-43. |
| [19] | Paternoster R, Brame R. (1997). Multiple routes to delinquency; A test of developmental and general theories of crime. Journal of criminology; 35: 45-84. |
| [20] | Piegorsch, W. W., (1990). Maximum likelihood estimation for the negative binomial dispersion parameter. Biometrics, 46: 863-867. |
| [21] | Venables, W. N. and Ripley, B. D. (2002) Modern Applied Statistics with S. Fourth edition. Springer. |
| [22] | Willkomm, D.; Machiraju, S. Bolot, J. Wolisz, A. (2009). Primary user behaviour in cellular network and implications for dynamic spectrum access. IEEE Communication magazine 47 (3); 88. |
APA Style
Nwakuya Maureen Tobechukwu, Nwabueze Joy Chioma. (2022). A Negative Binomial Regression on Road Accident Fatalities During COVID-19 Hit Era in Nigeria. International Journal of Statistical Distributions and Applications, 8(3), 40-46. https://doi.org/10.11648/j.ijsd.20220803.11
ACS Style
Nwakuya Maureen Tobechukwu; Nwabueze Joy Chioma. A Negative Binomial Regression on Road Accident Fatalities During COVID-19 Hit Era in Nigeria. Int. J. Stat. Distrib. Appl. 2022, 8(3), 40-46. doi: 10.11648/j.ijsd.20220803.11
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ijsd.20220803.11,
author = {Nwakuya Maureen Tobechukwu and Nwabueze Joy Chioma},
title = {A Negative Binomial Regression on Road Accident Fatalities During COVID-19 Hit Era in Nigeria},
journal = {International Journal of Statistical Distributions and Applications},
volume = {8},
number = {3},
pages = {40-46},
doi = {10.11648/j.ijsd.20220803.11},
url = {https://doi.org/10.11648/j.ijsd.20220803.11},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijsd.20220803.11},
abstract = {The incidence of road fatality in the world is most alarming. It is noted that the number of deaths in Nigeria by COVID-19 is nothing compared to the deaths by road accidents. As at July 2022 the total number of deaths by COVID-19 is 3,144 while the number of deaths by road accident is 10116, which is about 69% higher than deaths due to COVID-19. This paper hence considered the road accident fatalities during the COVID-19 hit period (2019-2021) in all the states of Nigeria. Due to the count nature of the response variable (Number of deaths) Poisson regression and the negative binomial regression are considered in other to build a model for predicting number of deaths due to road accidents. Both methods were compared to determine the most appropriate. The results of the analysis show that the number of male fatality is more than double that of the female and children with a percentage of 70.6%. The data revealed that Akwa Ibom State and Kaduna State have the minimum and the maximum number of deaths with 47 and 1070 respectively. The Poisson regression and Negative Binomial (NB) regression were considered for analysis. The data showed evidence of over-dispersion rendering the Poisson regression inadequate for the analysis, leaving the negative binomial regression as an alternative. Further assessment of the two models based on the mean-variance relationship, goodness of fit test, AIC and BIC, identified the NB as a better model for the analysis. The model considered the number of people killed as the response variable while the covariates include; speed limit, car issues, dangerous driving, fatigue, street light, bad roads and general factors. Applying the NB regression produced an end result model with only dangerous driving as a significant factor in road accidents fatalities. This shows that dangerous driving is the major cause of deaths on Nigerian roads. The paper also noted that based on the available data, road accidents is a more threatening fatal hazard than COVID-19 with a total death toll of 3,144 for COVID-19 and 10,116 for Road accidents in the same period considered. The paper suggests that the government should put more weight in curbing road accidents by instructing the road safety commission to focus more in developing new strategies or improving on the old strategies for eliminating or reducing dangerous driving by drivers on Nigerian roads.},
year = {2022}
}
TY - JOUR T1 - A Negative Binomial Regression on Road Accident Fatalities During COVID-19 Hit Era in Nigeria AU - Nwakuya Maureen Tobechukwu AU - Nwabueze Joy Chioma Y1 - 2022/08/17 PY - 2022 N1 - https://doi.org/10.11648/j.ijsd.20220803.11 DO - 10.11648/j.ijsd.20220803.11 T2 - International Journal of Statistical Distributions and Applications JF - International Journal of Statistical Distributions and Applications JO - International Journal of Statistical Distributions and Applications SP - 40 EP - 46 PB - Science Publishing Group SN - 2472-3509 UR - https://doi.org/10.11648/j.ijsd.20220803.11 AB - The incidence of road fatality in the world is most alarming. It is noted that the number of deaths in Nigeria by COVID-19 is nothing compared to the deaths by road accidents. As at July 2022 the total number of deaths by COVID-19 is 3,144 while the number of deaths by road accident is 10116, which is about 69% higher than deaths due to COVID-19. This paper hence considered the road accident fatalities during the COVID-19 hit period (2019-2021) in all the states of Nigeria. Due to the count nature of the response variable (Number of deaths) Poisson regression and the negative binomial regression are considered in other to build a model for predicting number of deaths due to road accidents. Both methods were compared to determine the most appropriate. The results of the analysis show that the number of male fatality is more than double that of the female and children with a percentage of 70.6%. The data revealed that Akwa Ibom State and Kaduna State have the minimum and the maximum number of deaths with 47 and 1070 respectively. The Poisson regression and Negative Binomial (NB) regression were considered for analysis. The data showed evidence of over-dispersion rendering the Poisson regression inadequate for the analysis, leaving the negative binomial regression as an alternative. Further assessment of the two models based on the mean-variance relationship, goodness of fit test, AIC and BIC, identified the NB as a better model for the analysis. The model considered the number of people killed as the response variable while the covariates include; speed limit, car issues, dangerous driving, fatigue, street light, bad roads and general factors. Applying the NB regression produced an end result model with only dangerous driving as a significant factor in road accidents fatalities. This shows that dangerous driving is the major cause of deaths on Nigerian roads. The paper also noted that based on the available data, road accidents is a more threatening fatal hazard than COVID-19 with a total death toll of 3,144 for COVID-19 and 10,116 for Road accidents in the same period considered. The paper suggests that the government should put more weight in curbing road accidents by instructing the road safety commission to focus more in developing new strategies or improving on the old strategies for eliminating or reducing dangerous driving by drivers on Nigerian roads. VL - 8 IS - 3 ER -
Information
Email: