, Volume 20, Issue 1, pp 95–116 | Cite as

Kernel density estimation based on Ripley’s correction

  • Arthur CharpentierEmail author
  • Ewen Gallic


In this paper, we investigate a technique inspired by Ripley’s circumference method to correct bias of density estimation of edges (or frontiers) of regions. The idea of the method was theoretical and difficult to implement. We provide a simple technique – based of properties of Gaussian kernels – to efficiently compute weights to correct border bias on frontiers of the region of interest, with an automatic selection of an optimal radius for the method. We illustrate the use of that technique to visualize hot spots of car accidents and campsite locations, as well as location of bike thefts.


Border bias Edge correction Frontier GIS Kernel density estimation Polygons Ripley’s circumference method Spatial process Visualization 



The authors would like to thank Olivier Scaillet and John Wilson for stimulating comments, and helping us to improve the paper, as well as three anonymous reviewers.


  1. 1.
    Bailey TC (1994) A review of statistical spatial analysis in geographical information systems. Spatial analysis and GIS, pp 13–44Google Scholar
  2. 2.
    Bailey TC, Gatrell AC (1995) Interactive spatial data analysis, vol 413. Longman Scientific & Technical EssexGoogle Scholar
  3. 3.
    Berman M, Diggle P (1989) Estimating weighted integrals of the second-order intensity of a spatial point process. J R Stat Soc Ser B Methodol 51:81–92Google Scholar
  4. 4.
    Black WR (1991) Highway accidents: a spatial and temporal analysis. Transp Res Rec 1318:75–82Google Scholar
  5. 5.
    Block CR, Dabdoub M, Fregly S (1995) Crime analysis through computer mapping. Police Executive Research Forum WashingtonGoogle Scholar
  6. 6.
    Bryc W (2002) A uniform approximation to the right normal tail integral. Appl Math Comput 127(2):365–374CrossRefGoogle Scholar
  7. 7.
    Ceccato V, Haining R (2004) Crime in border regions: The scandinavian case of öresund, 1998–2001. Ann Assoc Am Geogr 94(4):807–826Google Scholar
  8. 8.
    Chainey S, Reid S, Stuart N (2002) When is a hotspot a hotspot? A procedure for creating statistically robust hotspot maps of crime. Taylor & Francis, LondonGoogle Scholar
  9. 9.
    Chiu S-T (1991) Bandwidth selection for kernel density estimation. Ann Stat 19 (4):1883–1905CrossRefGoogle Scholar
  10. 10.
    Cressie N (1992) Statistics for spatial data. Terra Nova 4(5):613–617CrossRefGoogle Scholar
  11. 11.
    Davis KB (1975) Mean square error properties of density estimates. Ann Stat 3 (4):1025–1030CrossRefGoogle Scholar
  12. 12.
    Diggle P (1985) A kernel method for smoothing point process data. Appl Stat 34(2):138–147CrossRefGoogle Scholar
  13. 13.
    Eck JE (1997) What do those dots mean? mapping theories with data. Crime Mapping and Crime Prevention 8:379–406Google Scholar
  14. 14.
    Epanechnikov VA (1969) Non-parametric estimation of a multivariate probability density. Theory of Probability & Its Applications 14(1):153–158CrossRefGoogle Scholar
  15. 15.
    Erdogan S, Yilmaz I, Baybura T, Gullu M (2008) Geographical information systems aided traffic accident analysis system case study: city of Afyonkarahisar. Accid Anal Prev 40(1):174–181CrossRefGoogle Scholar
  16. 16.
    Everitt B, Landau S, Leese M, Stahl D (2011) Cluster analysis. Wiley series in probability and statistics. WileyGoogle Scholar
  17. 17.
    Getis A (1964) Temporal land-use pattern analysis with the use of nearest neighbor and quadrat methods. Ann Assoc Am Geogr 54(3):391–399CrossRefGoogle Scholar
  18. 18.
    Gisbert FJG (2003) Weighted samples, kernel density estimators and convergence. Empir Econ 28(2):335–351CrossRefGoogle Scholar
  19. 19.
    Hall P, Turlach BA (1999) Reducing bias in curve estimation by use of weights. Comput Stat Data Anal 30(1):67–86CrossRefGoogle Scholar
  20. 20.
    Hearnshaw HM, Unwin DJ, et al. (1994) Visualization in geographical information systems. Wiley, New YorkGoogle Scholar
  21. 21.
    Hsueh Y-H, Tseng H-Y (2013) Exploring the clustering location of accommodation units through the tourism development in the cing jing area of Taiwan. International Journal of Basic & Applied Sciences 13(4):34–39Google Scholar
  22. 22.
    Joly M-F (1992) Analytical approach to the identification of hazardous road locations: a review of the literatureGoogle Scholar
  23. 23.
    Kelsall JE, Diggle PJ (1995) Kernel estimation of relative risk. Bernoulli 1:3–16CrossRefGoogle Scholar
  24. 24.
    Levine N (2008) The “hottes” part of a hotspot: comments on “the utility of hotspot mapping for predicting spatial patterns of crime”. Secur J 21(4):295–302CrossRefGoogle Scholar
  25. 25.
    Levine N (2010) CrimeStat: a spatial statistics program for the analysis of crime incident locations (v 3.3)Google Scholar
  26. 26.
    Loo BP (2006) Validating crash locations for quantitative spatial analysis: a gis-based approach. Accid Anal Prev 38(5):879–886CrossRefGoogle Scholar
  27. 27.
    Marron J, Padgett W (1987) Asymptotically optimal bandwidth selection for kernel density estimators from randomly right-censored samples. Ann Stat 15(4):1520–1535CrossRefGoogle Scholar
  28. 28.
    Nakaya T, Yano K (2010) Visualising crime clusters in a space-time cube: an exploratory data-analysis approach using space-time kernel density estimation and scan statistics. Trans GIS 14(3):223–239CrossRefGoogle Scholar
  29. 29.
    Nguyen T (1991) Identification of accident blackspot locations: an overview. Number DP/91-4Google Scholar
  30. 30.
    Noland RB, Quddus MA (2004) A spatially disaggregate analysis of road casualties in England. Accid Anal Prev 36(6):973–984CrossRefGoogle Scholar
  31. 31.
    Ripley BD (1976) The second-order analysis of stationary point processes. J Appl Probab 13(2):255–266CrossRefGoogle Scholar
  32. 32.
    Ripley BD (1977) Modelling spatial patterns. J R Stat Soc Ser B Methodol 39:172–212Google Scholar
  33. 33.
    Ripley BD (1981) Spatial statistics. Wiley series in probability and mathematical statistics. WileyGoogle Scholar
  34. 34.
    Rogers A (1965) A stochastic analysis of the spatial clustering of retail establishments. J Am Stat Assoc 60(312):1094–1103CrossRefGoogle Scholar
  35. 35.
    Scott DW (2009) Multivariate density estimation: theory, practice, and visualization, vol 383. WileyGoogle Scholar
  36. 36.
    Shah AK (1985) A simpler approximation for areas under the standard normal curve. Am Stat 39(1):80–80Google Scholar
  37. 37.
    Silverman BW (1986) Density estimation for statistics and data analysis, vol 26. CRC PressGoogle Scholar
  38. 38.
    Steenberghen T, Dufays T, Thomas I, Flahaut B (2004) Intra-urban location and clustering of road accidents using gis: a belgian example. Int J Geogr Inf Sci 18(2):169–181CrossRefGoogle Scholar
  39. 39.
    Stefanski LA, Carroll RJ (1990) Deconvolving kernel density estimators. Statistics 21(2):169–184CrossRefGoogle Scholar
  40. 40.
    Tapia R, Thompson J (1978) Nonparametric probability density estimation. Johns Hopkins series in the mathematical sciences. Johns Hopkins University PressGoogle Scholar
  41. 41.
    Taylor P (1977) Quantitative methods in geography: an introduction to spatial analysis. Waveland PressGoogle Scholar
  42. 42.
    Thomas RW (1977) An introduction to quadrat analysis. Geo Abstracts LimitedGoogle Scholar
  43. 43.
    Van Patten IT, McKeldin-Coner J, Cox D (2009) A microspatial analysis of robbery: prospective hot spotting in a small city. Crime Mapping: A Journal of Research and Practice 1(1):7–32Google Scholar
  44. 44.
    Wand MP, Jones MC (1994) Kernel smoothing, vol 60. CRC PressGoogle Scholar
  45. 45.
    Xie Z, Yan J (2008) Kernel density estimation of traffic accidents in a network space. Comput Environ Urban Syst 32(5):396–406CrossRefGoogle Scholar
  46. 46.
    Yamada I, Rogerson PA (2003) An empirical comparison of edge effect correction methods applied to k-function analysis. Geogr Anal 35(2):97–109Google Scholar
  47. 47.
    Yamada I, Thill J-C (2004) Comparison of planar and network k-functions in traffic accident analysis. J Transp Geogr 12(2):149–158CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.UQAMMontréal (Québec)Canada
  2. 2.CREM UMR CNRS 6211, Université de Rennes 1Rennes CedexFrance

Personalised recommendations