Avaliação da dependência espacial na modelagem do desempenho da segurança viária em zonas de tráfego
TL;DR: In this article, a comparative analysis of modelos for previsao of acidentes is presented, with a focus on regresso de poisson geograficamente ponderada (RPGP).
read more
Abstract: Uma tecnica comumente usada no processo de modelagem do Desempenho da Seguranca Viaria (DSV), no nivel de planejamento, sao os Modelos Lineares Generalizados (MLG) assumindo a distribuicao binomial negativa para os erros. Limitacoes dessa tecnica, por nao considerar os efeitos espaciais, tem sido contornadas com a utilizacao de modelos espaciais locais a partir de tecnicas de regressao espacial como a Regressao de Poisson Geograficamente Ponderada (RPGP). Este trabalho tem por objetivo apresentar uma analise comparativa entre modelos de previsao de acidentes globais nao espaciais e locais espaciais para a estimacao do DSV agregado ao nivel de zonas de trafego em Fortaleza/CE. Foram calibrados modelos para a variavel dependente acidentes totais e acidentes com vitimas e os resultados mostraram que os modelos RPGP apre-sentaram melhor desempenho que os MLG nas medidas de ajustes e na reducao da autocorrelacao espacial dos residuos, sendo capazes de captar a heterogeneidade espacial da frequencia dos acidentes.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Dissertation
Metodologia baseada em SIG para predição de acidentes em rodovias rurais pista simples
Márcia Rejane Oliveira Barros Carvalho Macedo
- 28 May 2020
TL;DR: It is inferred that it is possible to develop a methodology to assess and analyze the impact that road geometry (horizontal curve) imposes on the increase in the number and severity of accidents on rural highways, which can be modeled by combining traditional statistical models and spatial analysis to predict accidents using GIS.
References
•Proceedings Article
Information Theory and an Extention of the Maximum Likelihood Principle
H. Akaike
- 01 Jan 1973
TL;DR: The classical maximum likelihood principle can be considered to be a method of asymptotic realization of an optimum estimate with respect to a very general information theoretic criterion to provide answers to many practical problems of statistical model fitting.
20.2K
Information Theory and an Extension of the Maximum Likelihood Principle
Hirotugu Akaike
- 01 Jan 1973
TL;DR: In this paper, it is shown that the classical maximum likelihood principle can be considered to be a method of asymptotic realization of an optimum estimate with respect to a very general information theoretic criterion.
16.3K
•Book
Geographically Weighted Regression: The Analysis of Spatially Varying Relationships
A. Fotheringham,Chris Brunsdon,Martin Charlton +2 more
- 11 Oct 2002
TL;DR: In this paper, the basic GWR model is extended to include local statistics and local models for spatial data, and a software for Geographically Weighting Regression is described. But this software is not suitable for the analysis of large scale data.
•Book
Observational Before-After Studies in Road Safety
Ezra Hauer
- 01 Feb 1997
TL;DR: In this paper, a three part monograph includes: the essentials; adaptations of conventional approaches; and elements of a new approach, which enables road safety researchers and professionals to interpret correctly the results of one of the main sources of knowledge about road safety engineering measures.
830
Geographically weighted Poisson regression for disease association mapping.
TL;DR: Geographically weighted Poisson regression and its semi-parametric variant are described as a new statistical tool for analysing disease maps arising from spatially non-stationary processes and GWPR provides disease analysts with an important new set of statistical tools.