Staffordshire University logo
STORE - Staffordshire Online Repository

Geographically weighted Poisson regression models with different kernels: application to road traffic accident data

AL-HASANI, Ghanim, ASADUZZAMAN, Md and SOLIMAN, Abdel-Hamid (2021) Geographically weighted Poisson regression models with different kernels: application to road traffic accident data. Communications in Statistics: Case Studies, Data Analysis and Applications. ISSN 2373-7484

[img] Text
Asaduzzaman_et_al_Comm_Stat_C_2020_Accepted_Version.pdf - AUTHOR'S ACCEPTED Version (default)
Restricted to Repository staff only until 25 January 2022.
Available under License All Rights Reserved (Under Embargo).

Download (1MB) | Request a copy

Abstract or description

Geographically weighted Poisson regression models (GWPR) are the class of spatial count regression models that capture the localisation effect on various influencing factors on the dependent variable. The main challenge with the GWPR models is to set appropriate kernel function to give weights for each neighbouring point during the model calibration. In this paper, we consider GWPR models for many different kernel functions, including box-car, bi-square, tri-cube, exponential and Gaussian function. Likelihood function, parameter estimation and model selection criteria have been shown in details. We applied the model formulation to the road traffic accident data in Oman as the country is one of the largest road traffic accident-prone countries in the Gulf region. Akaike information criterion (AIC), corrected Akaike information criterion (AICc) and geographically weighted deviance (GWD) have been used to assess the model fitting. The model with the exponential kernel weighted function provides the best fit for the data and captures the spatial heterogeneity and factors better with the exponential kernel weighting function.

Item Type: Article
Faculty: School of Creative Arts and Engineering > Engineering
Depositing User: Md ASADUZZAMAN
Date Deposited: 25 Jan 2021 16:15
Last Modified: 26 Jan 2021 04:30
URI: http://eprints.staffs.ac.uk/id/eprint/6777

Actions (login required)

View Item View Item

DisabledGo Staffordshire University is a recognised   Investor in People. Sustain Staffs
Legal | Freedom of Information | Site Map | Job Vacancies
Staffordshire University, College Road, Stoke-on-Trent, Staffordshire ST4 2DE t: +44 (0)1782 294000