Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Intensity estimation with log-linear Poisson model on linear networks

  • Idris Demirsoy (Computer Engineering, Usak University) ;
  • Fred W. Hufferb (Department of Statistics, Florida State University)
  • Received : 2022.06.02
  • Accepted : 2022.11.04
  • Published : 2023.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: The statistical analysis of point processes on linear networks is a recent area of research that studies processes of events happening randomly in space (or space-time) but with locations limited to reside on a linear network. For example, traffic accidents happen at random places that are limited to lying on a network of streets. This paper applies techniques developed for point processes on linear networks and the tools available in the R-package spatstat to estimate the intensity of traffic accidents in Leon County, Florida. Methods: The intensity of accidents on the linear network of streets is estimated using log-linear Poisson models which incorporate cubic basis spline (B-spline) terms which are functions of the x and y coordinates. The splines used equally-spaced knots. Ten different models are fit to the data using a variety of covariates. The models are compared with each other using an analysis of deviance for nested models. Results: We found all covariates contributed significantly to the model. AIC and BIC were used to select 9 as the number of knots. Additionally, covariates have different effects such as increasing the speed limit would decrease traffic accident intensity by 0.9794 but increasing the number of lanes would result in an increase in the intensity of traffic accidents by 1.086. Conclusion: Our analysis shows that if other conditions are held fixed, the number of accidents actually decreases on roads with higher speed limits. The software we currently use allows our models to contain only spatial covariates and does not permit the use of temporal or space-time covariates. We would like to extend our models to include such covariates which would allow us to include weather conditions or the presence of special events (football games or concerts) as covariates.

Keywords

References

  1. Administration U (2009). TIGER/Line Shapefile, 2018, county, Leon County, FL, All Roads County-based Shapefile, Data.Gov, 1, Available from: https://catalog.data.gov/dataset/tiger-line-%20shapefile-2018-county-leon-county-%20fl-all-roads-county-based-shapefile
  2. Agresti A (2003). Categorical Data Analysis, John Wiley & Sons, New Jersey.
  3. Ang Q, Baddeley A, and Nair G (2012). Geometrically corrected second order analysis of events on a linear network, with applications to ecology and criminology, Scandinavian Journal of Statistics, 39, 591-617. https://doi.org/10.1111/j.1467-9469.2011.00752.x
  4. Atilgan T and Bozdogan H (1990). Selecting the number of knots in fitting cardinal B splines for density estimation using AIC, Journal of the Japan Statistical Society, Japanese Issue, 20, 179-190.
  5. Baddeley A, Rubak E, and Turner R (2015). Spatial Point Patterns: Methodology and Applications with R, Chapman, New York.
  6. Berman M and Turner T (1992). Approximating point process likelihoods with GLIM, Applied Statistics, 41, 31-38. https://doi.org/10.2307/2347614
  7. Bivand R, Pebesma E, Gomez-Rubio V, and Pebesma E (2008). Applied Spatial Data Analysis with R, Springer, New York.
  8. Engel C (2017). Introduction to spatial data types in R, Introduction to Spatial Data Types in R, 5, Available from: https://cengel.github.io%20/rspatial/2%5CspDataTypes.nb.html
  9. Transportation F (1996). undefined. FDOT Open Data Hub, 1, Available from: https://gis-fdot.opendata.arcgis.com/
  10. Illian J, Penttinen A, Stoyan H, and Stoyan D (2008). Statistical Analysis and Modelling of Spatial Point Patterns, John Wiley & Sons, Chichester.
  11. Johnson T (2010). Introduction to Spatial Point Processes, University of Warwick, Coventry.
  12. Last G and Penrose M (2017). Lectures on the Poisson Process, Cambridge University Press, Cambridge.
  13. Likhachev D (2017). Selecting the right number of knots for B-spline parameterization of the dielectric functions in spectroscopic ellipsometry data analysis, Thin Solid Films, 636, 519-526. https://doi.org/10.1016/j.tsf.2017.06.056
  14. Lowy, J (2014). Traffic accidents in the U.S. cost $871 billion a year, federal study finds, PBS, 5, Available from: https://www.pbs.org/newshour/nation/motor-vehicle-crashes
  15. Mc Swiggan G, Baddeley A, and Nair G (2017). Kernel density estimation on a linear network, Scandinavian Journal of Statistics, 44, 324-345. https://doi.org/10.1111/sjos.12255
  16. Moradi M, Cronie O, Rubak E, Lachieze-Rey R, Mateu J, and Baddeley A (2019). Resample-smoothing of Voronoi intensity estimators, Statistics and Computing, 29, 995-1010. https://doi.org/10.1007/s11222-018-09850-0
  17. Okabe A, Satoh T, and Sugihara K (2009). A kernel density estimation method for networks, its computational method and a GIS-based tool, International Journal of Geographical Information Science, 23, 7-32. https://doi.org/10.1080/13658810802475491
  18. Okabe A and Sugihara K (2012). Spatial Analysis along Networks: Statistical and Computational Methods, John Wiley & Sons, New York.
  19. Xie Z and Yan J (2008). Kernel density estimation of traffic accidents in a network space, Computers, Environment and Urban Systems, 32, 396-406. https://doi.org/10.1016/j.compenvurbsys.2008.05.001
  20. Zimmerman D (2008). Estimating the intensity of a spatial point process from locations coarsened by incomplete geocoding, Biometrics, 64, 262-270. https://doi.org/10.1111/j.1541-0420.2007.00870.x