Abstract
This paper provides a short review of modern smoothing methods for density and distribution functions dealing with circular data. We highlight the usefulness of circular kernels for smooth density estimation in this context and contrast it with smooth density estimation based on orthogonal series. It is seen that the wrapped Cauchy kernel as a choice of circular kernel appears as a natural candidate as it has a close connection to orthogonal series density estimation on a unit circle. In the literature, the use of von Mises circular kernel is investigated, which requires the numerical computation of the Bessel function. On the other hand, the wrapped Cauchy kernel is much simpler to use. This adds further weight to the considerable role of the wrapped Cauchy distribution in circular statistics. We also investigate some transformation-based methods in adapting the linear kernel density estimator to the circular data. This is very useful in practice as widely available software on linear kernel density estimation can easily be adapted to the circular case. These simpler methods are illustrated using some real data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Abe, T., Pewsey, A., Shimizu, K.: On Papakonstantinou’s extension of the cardioid distribution. Statist. Prob. Lett. 79, 2138–2147 (2009)
Babu, G.J., Canty, A., Chaubey, Y.P.: Application of Bernstein polynomials for smooth estimation of a distribution and density function. J. Statist. Plann. Inference 105, 377–392 (2002)
Babu, G.J., Chaubey, Y.P.: Smooth estimation of a distribution and density function on hypercube using Bernstein polynomials for dependent random vectors. Statist. Prob. Lett. 76, 959–969 (2006)
Bai, Z.D., Rao, C.R., Zhao, L.C.: Kernel estimators of density function of directional data. J. Multivariate Anal. 27, 24–39 (1988)
Batschelet, E.: Circular Statistics in Biology. Academic Press, London (1981)
Buckland, S.T.: Fitting density functions with polynomials. J. Royal Statist. Soc. A41, 63–76 (1992)
Cao, Y.: On Transformation Based Circular Density Estimators. MSc. Thesis, Concordia University (2018). https://spectrum.library.concordia.ca/983905/1/Cao_MSc_f2018.pdf
Carnicero, J.A., Wiper, M.P., Ausín, M.C.: Circular Bernstein polynomial distributions. In: Working Paper 10-25, Statistics and Econometrics Series 11, Departamento de Estadística Universidad Carlos III de Madrid (2010). https://e-archivo.uc3m.es/bitstream/handle/10016/8318/ws102511.pdf?sequence=1
Cartwright, D.E.: The use of directional spectra in studying the output of a wave recorder on a moving ship. In: Ocean Wave Spectra, pp. 203–218. Prentice-Hall, Englewood Cliffs, NJ (1963)
Čencov, N.N.: Evaluation of an unknown distribution density from observations. Soviet Math. Doklady 3, 1559–1562 (1962)
Čencov, N.N.: Statistical Decision Rules and Optimum Inference. Springer, New York (1980)
Chaubey, Y.P.: Smooth kernel estimation of a circular density function: a connection to orthogonal polynomials on the unit circle. J. Prob. Statist. (2018) Article ID 5372803.https://doi.org/10.1155/2018/5372803
Chaubey, Y.P., Li, J., Sen, A., Sen, P.K.: A new smooth density estimator for non-negative random variables. J. Indian Statist. Assoc. 50, 83–104 (2012)
Devroye, L., Györfi, L.: Nonparametric Density Estimation: The \(L_1\) View. John Wiley & Sons, New York (1985)
Devroye, L., Györfi, L.: Combinatorial Methods in Density Estimation. Springer, New York (2001)
Di Marzio, M., Panzera, A., Taylor, C.C.: Local polynomial regression for circular predictors. Statist. Prob. Lett. 79(19), 2066–2075 (2009)
Di Marzio, M., Panzera, A., Taylor, C.C.: Kernel density estimation on the torus. J. Statist. Plann. Inference 141, 2156–2173 (2011)
Efromvich, S.: Nonparametric Curve Estimation: Methods, Theory, and Applications. Springer, New York (1999)
Efromvich, S.: Orthogonal series density estimation. Wiley Interdisc. Rev. 2, 467–476 (2010)
Eğecioğlu, Ö., Srinivasan, A.: Efficient nonparametric density estimation on the sphere with applications in fluid mechanics. SIAM J. Sci. Comput. 22, 152–176 (2000)
Feller, W.: An Introduction to Probability Theory and its Applications, vol. II. John Wiley & Sons, New York (1965)
Fernández-Durán, J.J.: Circular distributions based on nonnegative trigonometric sums. Biometrics 60, 499–503 (2004)
Fisher, N.I.: Smoothing a sample of circular data. J. Struct. Geol. 11, 775–778 (1989)
Fisher, N.I.: Statistical Analysis Circular Data. Cambridge University Press, Cambridge (1993)
Hall, P.: Estimating a density on the positive half line by the method of orthogonal series. Ann. Inst. Statist. Math. 32, 351–362 (1980)
Hall, P.: On trigonometric series estimates of densities. Ann. Statist. 9, 683–685 (1981)
Hall, P., Watson, G.P., Cabrera, J.: Kernel density estimation for spherical data. Biometrika 74(4), 751–762 (1987)
Hart, J.D.: Nonparametric Smoothing and Lack-of-Fit Tests. Springer, New York (1997)
Jammalamadaka, S.R., SenGupta, A.: Topics in Circular Statistics. World Scientific, Singapore (2001)
Klemelä, J.: Estimation of densities and derivatives of densities with directional data. J. Multivariate Anal. 73, 18–40 (2000)
Mardia, K.V.: Statistics of directional data. J. Royal Statist. Soc. Ser. B Methodol. 37, 349–393 (1975)
Mhaskar, H.N., Pai, D.V.: Fundamentals of Approximation Theory. Narosa Publishing House, New Delhi (2000)
Mooney, A., Helms, P.J., Jolliffe, I.T.: Fitting mixtures of von Mises distributions: a case study involving sudden infant death syndrome. Comput. Statist. Data Anal. 41, 505–513 (2003)
Oliveira, M., Crujeiras, R.M., Rodríguez-Casal, A.: A plug-in rule for bandwidth selection in circular density estimation. Comput. Statist. Data Anal. 56, 3898–3908 (2012)
Oliveira, M., Crujeiras, R. M., Rodríguez-Casal, A.: NPCirc: Nonparametric Circular Methods. R package version 2.0.1 (2014). http://www.CRAN.R-project.org/package=NPCirc
Papakonstantinou, V.: Beiträge zur zirkulären Statistik. Ph.D. dissertation, University of Zurich, Switzerland (1979)
Parzen, E.: On estimation of a probability density function and mode. Ann. Math. Statist. 33, 1065–1076 (1962)
Prakasa Rao, B.L.S.: Non Parametric Functional Estimation. Academic Press, Orlando, Florida (1983)
Rudzkis, R., Radavicius, M.: Adaptive estimation of distribution density in the basis of algebraic polynomials. Theor. Prob. Appl. 49, 93–109 (2005)
Rosenblatt, M.: Remarks on some nonparametric estimates of a density function. Ann. Math. Statist. 27, 832–837 (1956)
Seshadri, V.: A family of distributions related to the McCullagh family. Statist. Prob. Lett. 12, 373–378 (1991)
Simon, B.: Orthogonal Polynomials on the Unit Circle, Part 1: Classical Theory. American Mathematical Society, Providence, Rhode Island (2005)
Silverman, B.W.: Density Estimation for Statistics and Data Analysis. Chapman & Hall, London (1986)
Tarter, M.E., Lock, M.D.: Model-Free Curve Estimation. Chapman & Hall, London (1993)
Taylor, C.C.: Automatic bandwidth selection for circular density estimation. Comput. Statist. Data Anal. 52, 3493–3500 (2008)
Trefthen, L.N.: Approximation Theory and Approximation Practice. SIAM, Philadelphia (2013)
Vitale, R.A.: A Bernstein polynomial approach to density estimation. In: Puri, M.L. (Eds.), Inference, Statistical, Topics, Related, vol. 2, pp. 87–100. Academic Press, New York (1975)
Walter, G.G.: Properties of Hermite series estimation of probability density. Ann. Stat. 5, 1258–1264 (1977)
Walter, G.G.: Wavelets and Other Orthogonal Systems with Applications. CRC Press, London (1994)
Acknowledgements
The author is thankful to anonymous reviewers for helpful comments that have helped to improve the presentation of this paper. The partial support for this research from the Natural Sciences and Engineering Research Council of Canada through a Discovery Grant to the author is also gratefully acknowledged.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix: Some Preliminary Results from Complex Analysis
Appendix: Some Preliminary Results from Complex Analysis
Let \(\mathbb {D}\) be the open unit disk, \(\{z~| ~|z|<1\},\) in \(\mathbb {Z}\) and let \(\mu \) be a continuous measure defined on the boundary \(\partial \mathbb {D},\) i.e., the circle \(\{z~|~ |z|=1\}.\) The point \(z\in \mathbb {D}\) will be represented by \(z=r\mathrm{e}^{i\theta }\) for \(r\in [0,1), \theta \in [0,2\pi )\) and \(i=\sqrt{-1}.\)
A standard result in complex analysis involves the Poisson representation that involves the real and complex Poisson kernels that are defined as
for \(\theta ,\varphi \in [0,2\pi )\) and \(r\in [0,1)\) and by
for \(\omega \in \partial \mathbb {D}\) and \(z\in \mathbb {D}.\) The connection between the kernels (33) and (34) is given by the fact that
The Poisson representation says that if g is analytic in a neighborhood of \(\bar{\mathbb {D}}\) with g(0) real, then for \(z\in \mathbb {D},\)
(see [42, p. 27]). This representation leads to the result (see (ii) in §5 of [42]) that for Lebesgue a.e. \(\theta ,\)
exists and if \(d\mu =w(\theta )\frac{d\theta }{2\pi }+d\mu _s\) with \(d\mu _s\) singular, then
where
Our strategy for smooth estimation is the fact that for \(d\mu _s=0\) we have
where now W(z) is defined as
We define the estimator of \(f(\theta )\) motivated by considering an estimator of W(z), the identity (36) and (37), i.e.
where
and r has to be chosen appropriately. Recognize that (39) has the representation
where \(\omega _j={\mathrm{e}^{i\theta _j}},\) then using (35), we have
and therefore (38) becomes
that is of the same form as in (9).
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Chaubey, Y.P. (2022). On Nonparametric Density Estimation for Circular Data: An Overview. In: SenGupta, A., Arnold, B.C. (eds) Directional Statistics for Innovative Applications. Forum for Interdisciplinary Mathematics. Springer, Singapore. https://doi.org/10.1007/978-981-19-1044-9_19
Download citation
DOI: https://doi.org/10.1007/978-981-19-1044-9_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-1043-2
Online ISBN: 978-981-19-1044-9
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)