Robust estimation of the spherical normal distribution

• Autorzy: Castilla Elena

Identyfikatory

DOI

10.14708/ma.v50i1.7119

Warianty tytułu

PL

Odporna estymacja parametrów sferycznego rozkładu normalnego

• Języki publikacji: EN

Abstrakty

EN

This paper develops a new family of estimators, the minimum density power divergence estimators, for the parameters of the Spherical Normal Distribution. This family contains the maximum likelihood estimator as a particular case. The robustness is empirically illustrated through a Monte Carlo simulation study and two biological numerical examples. Tools needed to implement these methods are also provided.

PL

Artykuł przedstawia nową rodzinę estymatorów parametrów sferycznego rozkładu normalnego minimalnej dywergencji. Ta rodzina obejmuje estymator największej wiarygodności jako przypadek szczególny. Odporność tych estymatorów jest zilustrowana empirycznie przez badanie symulacyjne Monte Carlo. Zamieszczone przykłady dla danych rzeczywistych dotyczą zagadnień z biologii. Pokazano również narzędzia potrzebne do wdrożenia tych metod.

Słowa kluczowe

EN

directional data; divergence; robustness; spherical normal distribution

PL

dane kierunkowe; rozbieżność; odporność; sferyczny rozkład normalny

• Wydawca: Polskie Towarzystwo Matematyczne
• Czasopismo: Mathematica Applicanda
• Rocznik: 2022
• Tom: Vol. 50, no. 1
• Strony: 43--63
• Opis fizyczny: Bibliogr. 38 poz., rys., tab,. wykr.

Twórcy

autor

Castilla Elena

• Universidad Rey Juan Carlos Department of Applied Mathematics Calle Tulipán. 28933 Móstoles, Madrid, Spain

• https://orcid.org/0000-0002-9626-6449

Bibliografia

• [1] C. Agostinelli. Robust estimation for circular data. Comput. Statist. Data Anal., 51(12):5867–5875, 2007.
• [2] R. B. Arellano-Valle, G. del Pino, and P. Iglesias. Bayesian inference in spherical linear models: robustness and conjugate analysis. J. Multivariate Anal., 97(1):179–197, 2006.
• [3] M. Bangert, P. Hennig, and U. Oelfke. Using an infinite von Mises-fisher mixture model to cluster treatment beam directions in external radiation therapy. In S. Draghici, T. M. Khoshgoftaar, V. Palade, W. Pedrycz, M. A. Wani, and X. Zhu, editors, ICMLA, pages 746–751. IEEE Computer Society, 2010.
• [4] A. Basu, I. R. Harris, N. L. Hjort, and M. C. Jones. Robust and efficient estimation by minimising a density power divergence. Biometrika, 85(3):549–559, 1998.
• [5] J. Bergstra and Y. Bengio. Random search for hyper-parameter optimization. J. Mach. Learn. Res., 13:281–305, 2012.
• [6] D. P. Bertsekas. On penalty and multiplier methods for constrained minimization. SIAM J. Control Optim., 14(2):216–235, 1976.
• [7] A. Bhattacharya and R. Bhattacharya. Nonparametric inference on manifolds with applications to shape spaces., volume 2 of Institute of Mathematical Statistics (IMS) Monographs. Cambridge University Press, Cambridge, 2012.
• [8] E. Castilla and P. Chocano. On the choice of the optimal tuning parameter in robust one-shot device testing analysis., volume 445 of Trends in Mathematical, Information and Data Sciences. Studies in Systems, Decision and Control, pages 169–180. Springer, Cham, 2023.
• [9] D. Collett. Outliers in circular data. Journal of the Royal Statistical Society: Series C (Applied Statistics), 29(1):50–57, 1980.
• [10] N. De Cao and W. Aziz. The power spherical distribution. arXiv preprint arXiv:2006.04437, 2020.
• [11] Y. Demir and Ö. C. Bilgin. Application of circular statistics to life science data. Medical Science and Discovery, 6(3):63–72, 2019.
• [12] D. E. Ferguson, H. F. Landreth, and J. P. Mckeown. Sun compass orientation of the northern cricket frog, acris crepitans. Animal Behaviour, 15(1):45–53, 1967.
• [13] N. I. Fisher. Statistical analysis of circular data. Cambridge University Press, Cambridge, 1993.
• [14] J. Gill and D. Hangartner. Circular data in political science and how to handle it. Political Analysis, 18(3):316–336, 2010.
• [15] W. C. Guenther and P. J. Terragno. A review of the literature on a class of coverage problems. Ann. Math. Statist., 35:232–260, 1964.
• [16] S. Hauberg. Directional statistics with the spherical normal distribution. In 2018 21st International Conference on Information Fusion (FUSION), pages 704–711. IEEE, 2018.
• [17] S. Kato and S. Eguchi. Robust estimation of location and concentration parameters for the von Mises–Fisher distribution. Statist. Papers, 57(1): 205–234, 2016.
• [18] J. T. Kent. The Fisher-Bingham distribution on the sphere. J. Roy. Statist. Soc. Ser. B, 44(1):71–80, 1982.
• [19] C. G. Khatri and K. V. Mardia. The von Mises-Fisher matrix distribution in orientation statistics. J. Roy. Statist. Soc. Ser. B, 39(1):95–106, 1977.
• [20] D. Ko and P. Guttorp. Robustness of estimators for directional data. Ann. Statist., 16(2):609–618, 1988.
• [21] A. K. Laha and K. C. Mahesh. SB-robustness of directional mean for circular distributions. J. Statist. Plann. Inference, 141(3):1269–1276, 2011.
• [22] L. Landler, G. D. Ruxton, and E. P. Malkemper. Circular data in biology: advice for effectively implementing statistical procedures. Behavioral Ecology and Sociobiology, 72(8):1–10, 2018.
• [23] U. Lund, C. Agostinelli, and M. C. Agostinelli. Package ‘circular’. Repository CRAN, pages 1–142, 2017. URL https://cran.r-project.org/web/packages/circular/index.html.
• [24] K. Mardia and P. Zemroch. Algorithm as 86: The von Mises distribution function. Journal of the Royal Statistical Society. Series C (Applied Statistics), 24(2):268–272, 1975.
• [25] M. Moghimbeygi and M. Golalizadeh. A new extension of von Mises–Fisher distribution. Hacet. J. Math. Stat., 50(6):1838–1854, 2021.
• [26] B. S. Otieno. An alternative estimate of preferred direction for circular data. ProQuest LLC, Ann Arbor, MI, 2002. Thesis (Ph.D.)–Virginia Polytechnic Institute and State University.
• [27] M. Papadakis, M. Tsagris, M. Dimitriadis, S. Fafalios, I. Tsamardinos, M. Fasiolo, G. Borboudakis, J. Burkardt, C. Zou, K. Lakiotaki, and C. Chatzipantsiou. A Collection of Efficient and Extremely Fast R Functions, 2021. URL https://cran.r-project.org/web/packages/Rfast/index.html. Package ‘Rfast’ Version 2.0.6.
• [28] X. Pennec. Intrinsic statistics on riemannian manifolds: Basic tools for geometric measurements. Journal of Mathematical Imaging and Vision, 25(1):127–154, 2006.
• [29] J. W. Pratt, H. Raiffa, and R. Schlaifer. Introduction to statistical decision theory. MIT Press, Cambridge, MA, 1995.
• [30] H. Ruben. Probability content of regions under spherical normal distributions. I. Ann. Math. Statist., 31:598–618, 1960a.
• [31] H. Ruben. Probability content of regions under spherical normal distributions. II. The distribution of the range in normal samples. Ann. Math. Statist., 31:1113–1121, 1960b.
• [32] H. Ruben. Probability content of regions under spherical normal distributions. III. The bivariate normal integral. Ann. Math. Statist., 32:171–186, 1961.
• [33] H. Ruben. Probability content of regions under spherical normal distributions. IV. The distribution of homogeneous and non-homogeneous quadratic functions of normal variables. Ann. Math. Statist., 33:542–570, 1962.
• [34] H. Salehian, R. Chakraborty, E. Ofori, D. Vaillancourt, and B. C. Vemuri. An efficient recursive estimator of the Fréchet mean on a hypersphere with applications to medical image analysis. Mathematical Foundations of Computational Anatomy, 3:143–154, 2015.
• [35] S. Sugasawa and S. Yonekura. On selection criteria for the tuning parameter in robust divergence. Entropy, 23(9):Paper No. 1147, 10, 2021.
• [36] J. Warwick and M. C. Jones. Choosing a robustness tuning parameter. J. Stat. Comput. Simul., 75(7):581–588, 2005.
• [37] K. You. Topics in Geometric and Topological Data Analysis. ProQuest LLC, Ann Arbor, MI, 2021. Thesis (Ph.D.)–University of Notre Dame.
• [38] K. You and C. Suh. Parameter estimation and model-based clustering with spherical normal distribution on the unit hypersphere. Comput. Statist. Data Anal., 171:Paper No. 107457, 2022.

Uwagi

PL

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).