Abstract
Kernel smoothing of spatial point data can often be improved using an adaptive, spatially varying bandwidth instead of a fixed bandwidth. However, computation with a varying bandwidth is much more demanding, especially when edge correction and bandwidth selection are involved. This paper proposes several new computational methods for adaptive kernel estimation from spatial point pattern data. A key idea is that a variable-bandwidth kernel estimator for d-dimensional spatial data can be represented as a slice of a fixed-bandwidth kernel estimator in \((d+1)\)-dimensional scale space, enabling fast computation using Fourier transforms. Edge correction factors have a similar representation. Different values of global bandwidth correspond to different slices of the scale space, so that bandwidth selection is greatly accelerated. Potential applications include estimation of multivariate probability density and spatial or spatiotemporal point process intensity, relative risk, and regression functions. The new methods perform well in simulations and in two real applications concerning the spatial epidemiology of primary biliary cirrhosis and the alarm calls of capuchin monkeys.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Abramson, I.S.: On bandwidth estimation in kernel estimates—a square root law. Ann. Stat. 10(4), 1217–1223 (1982)
Baddeley, A.J., Turner, R.: spatstat: an R package for analyzing spatial point patterns. J. Stat. Softw. 12(6), 1–42 (2005)
Baddeley, A., Rubak, E., Turner, R.: Spatial Point Patterns: Methodology and Applications with R. Chapman and Hall/CRC Press, London (2015)
Bernacchia, A., Pigolotti, S.: Self-consistent method for density estimation. J. R. Stat. Soc. Ser. B 73, 407–422 (2011)
Bithell, J.F.: An application of density estimation to geographical epidemiology. Stat. Med. 9, 691–701 (1990)
Bithell, J.F.: Estimation of relative risk functions. Stat. Med. 10, 1745–1751 (1991)
Breiman, L., Meisel, W., Purcell, E.: Variable kernel estimates of multivariate densities. Technometrics 19, 135–144 (1977)
Campos, F.A., Fedigan, L.M.: Spatial ecology of perceived predation risk and vigilance behavior in white-faced capuchins. Behav. Ecol. 25, 477–486 (2014)
Chaudhuri, P., Marron, J.: Scale space view of curve estimation. Ann. Stat. 28, 408–428 (2000)
Cooley, J.W., Tukey, J.W.: An algorithm for the machine calculation of complex Fourier series. Math. Comput. 19, 297–301 (1965)
Davies, T.M., Hazelton, M.L.: Adaptive kernel estimation of spatial relative risk. Stat. Med. 29(23), 2423–2437 (2010)
Davies, T.M., Jones, K., Hazelton, M.L.: Symmetric adaptive smoothing regimens for estimation of the spatial relative risk function. Comput. Stat. Data Anal. 101, 12–28 (2016)
Diggle, P.J.: A kernel method for smoothing point process data. Appl. Stat. 34(2), 138–147 (1985)
Diggle, P.: Nonparametric methods. In: Gelfand, A., Diggle, P., Fuentes, M., Guttorp, P. (eds.) Handbook of Spatial Statistics, Chapter 18, pp. 299–316. CRC Press, Boca Raton (2010)
Diggle, P.J., Marron, J.S.: Equivalence of smoothing parameter selectors in density and intensity estimation. J. Am. Stat. Assoc. 83, 793–800 (1988)
Duong, T.: ks: kernel density estimation and kernel discriminant analysis for multivariate data in R. J. Stat. Softw. 21(7), 1–16 (2007)
Duong, T., Hazelton, M.L.: Plug-in bandwidth matrices for bivariate kernel density estimation. J. Nonparametr. Stat. 15(1), 17–30 (2003)
Duong, T., Hazelton, M.L.: Cross-validation bandwidth matrices for multivariate kernel density estimation. Scand. J. Stat. 32, 485–506 (2005)
Faraway, J.J., Jhun, M.: Bootstrap choice of bandwidth for density estimation. J. Am. Stat. Assoc. 85, 1119–1122 (1990)
Fernando, W.T.P.S., Hazelton, M.L.: Generalizing the spatial relative risk function. Spat. Spatio-Temporal Epidemiol. 8, 1–10 (2014)
Gramacki, A., Gramacki, J.: FFT-based fast bandwidth selector for multivariate kernel density estimation. Comput. Stat. Data Anal. 106, 27–45 (2017a)
Gramacki, A., Gramacki, J.: FFT-based fast computation of multivariate kernel density estimators with unconstrained bandwidth matrices. J. Comput. Graph. Stat. 26, 459–462 (2017b)
Hall, P., Marron, J.S.: Variable window width kernel density estimates of probability densities. Probab. Theory Relat. Fields 80, 37–49 (1988)
Hall, P., Marron, J.S., Park, B.U.: Smoothed cross-validation. Probab. Theory Relat. Fields 92, 1–20 (1992)
Harris, F.: On the use of windows for harmonic analysis with the discrete Fourier transform. Proc. IEEE 66(1), 51–83 (1978)
Hu, S., Poskitt, D.S., Zhang, X.: Bayesian adaptive bandwidth kernel density estimation of irregular multivariate distributions. Comput. Stat. Data Anal. 56, 732–740 (2012)
Jones, M.C.: Simple boundary correction for kernel density estimation. Stat. Comput. 3, 135–146 (1993)
Jones, M.C., Marron, J.S., Sheather, S.J.: A brief survey of bandwidth selection for density estimation. J. Am. Stat. Assoc. 91, 401–407 (1996)
Kelsall, J.E., Diggle, P.J.: Kernel estimation of relative risk. Bernoulli 1, 3–16 (1995)
Koch, K., Ohser, J., Schladitz, K.: Spectral theory for random closed sets and estimating the covariance via frequency space. Adv. Appl. Probab. 35, 603–613 (2003)
Loftsgaarden, D.O., Quesenberry, C.P.: A nonparametric estimate of a multivariate density function. Ann. Math. Stat. 36, 1049–1051 (1965)
Marshall, J.C., Hazelton, M.L.: Boundary kernels for adaptive density estimators on regions with irregular boundaries. J. Multivar. Anal. 101, 949–963 (2010)
Møller, J., Syversveen, A.R., Waagepetersen, R.P.: Log Gaussian Cox processes. Scand. J. Stat. 25, 451–482 (1998)
O’Brien, T.A., Kashinath, K., Cavanaugh, N.R., Collins, W.D., O’Brien, J.P.: A fast and objective multidimensional kernel density estimation method: fastKDE. Comput. Stat. Data Anal. 101, 148–160 (2016)
Pinsky, M.: Introduction to Fourier Analysis and Wavelets. No. 102 in Graduate Studies in Mathematics. American Mathematical Society, Providence (2002)
Prince, M.I., Chetwynd, A., Diggle, P.J., Jarner, M., Metcalf, J.V., James, O.F.W.: The geographical distribution of primary biliary cirrhosis in a well-defined cohort. Hepatology 34, 1083–1088 (2001)
R Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna (2017). https://www.R-project.org/
Sain, S.R.: Multivariate locally adaptive density estimation. Comput. Stat. Data Anal. 39, 165–186 (2002)
Sain, S.R., Scott, D.W.: On locally adaptive density estimation. J. Am. Stat. Assoc. 91, 1525–1534 (1996)
Sain, S.R., Baggerly, K.A., Scott, D.W.: Cross-validation of multivariate densities. J. Am. Stat. Assoc. 89, 807–817 (1994)
Silverman, B.W.: Kernel density estimation using the fast Fourier transform. Appl. Stat. 31, 93–99 (1982)
Silverman, B.W.: Density Estimation for Statistics and Data Analysis. Chapman and Hall, New York (1986)
Taylor, C.C.: Bootstrap choice of the smoothing parameter in kernel density estimation. Biometrika 76, 705–712 (1989)
Terrell, G.R.: The maximal smoothing principle in density estimation. J. Am. Stat. Assoc. 85, 470–477 (1990)
Terrell, G.R., Scott, D.W.: Variable kernel density estimation. Ann. Stat. 20, 1236–1265 (1992)
Wand, M.P.: Fast computation of multivariate kernel estimators. J. Comput. Graph. Stat. 3(4), 433–445 (1994)
Wand, M.P., Jones, M.C.: Comparison of smoothing parameterizations in bivariate kernel density estimation. J. Am. Stat. Assoc. 88, 520–528 (1993)
Wand, M.P., Jones, M.C.: Kernel Smoothing. Chapman and Hall, Boca Raton (1995)
Zhang, X., King, M.L., Hyndman, R.J.: A Bayesian approach to bandwidth selection for multivariate kernel density estimation. Comput. Stat. Data Anal. 50, 3009–3031 (2006)
Acknowledgements
The authors gratefully acknowledge Fernando A. Campos and Linda M. Fedigan for providing the capuchin data and advice related to their original analysis. Two referees and an associate editor are thanked for their constructive feedback.
Author information
Authors and Affiliations
Corresponding author
Additional information
TMD was supported in part by the Royal Society of New Zealand, Marsden Fast-start Grant 15-UOO-092: Smoothing and inference for point process data with applications to epidemiology. AB was supported in part by the Australian Research Council, Discovery Outstanding Researcher Award DP130104470.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Davies, T.M., Baddeley, A. Fast computation of spatially adaptive kernel estimates. Stat Comput 28, 937–956 (2018). https://doi.org/10.1007/s11222-017-9772-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11222-017-9772-4