Abstract
In contemporary data analytics, one often models uncertainty-prone data as samples stemming from a sequence of independent random variables whose distributions are non-identical but linked by a common (scalar or multidimensional) parameter. For such a context, we present in the current Part I a new robustness-featured parameter-estimation framework, in terms of minimization of the scaled Bregman power distances of Stummer and Vajda [23] (see also [21]); this leads to a wide range of outlier-robust alternatives to the omnipresent (non-robust) method of maximum-likelihood-examination, and extends the corresponding method of Ghosh and Basu [7]. In Part II (see [20]), we provide some applications of our framework to data from potentially rare but dangerous events described by approximate extreme value distributions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Sigma-finite measure.
References
Amari, S.-I.: Information Geometry and Its Applications. Springer, Tokyo (2016)
Amari, S.-I., Nagaoka, H.: Methods of Information Geometry. Oxford University Press, Oxford (2000)
Ay, N., Jost, J., Lê, H.V., Schwachhöfer, L.: Information Geometry. EMGFASMSM, vol. 64. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-56478-4
Basu, A., Harris, I.R., Hjort, N.L., Jones, M.C.: Robust and efficient estimation by minimizing a density power divergence. Biometrika 85(3), 549–559 (1998)
Basu, A., Shioya, H., Park, C.: Statistical Inference: The Minimum Distance Approach. CRC Press, Boca Raton (2011)
Broniatowski, M., Stummer, W.: Some universal insights on divergences for statistics, machine learning and artificial intelligence. In: Nielsen, F. (ed.) Geometric Structures of Information. SCT, pp. 149–211. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-02520-5_8
Ghosh, A., Basu, A.: Robust estimation for independent non-homogeneous observations using density power divergence with applications to linear regression. Electron. J. Stat. 7, 2420–2456 (2013)
Ghosh, A., Basu, A.: Robust estimation in generalized linear models: the density power divergence approach. TEST 25, 269–290 (2016)
Ghosh, A.: Divergence based robust estimation of the tail index through an exponential regression model. Stat. Methods Appl. 26, 181–213 (2017)
Ghosh, A., Basu, A.: Robust bounded influence tests for independent non-homogeneous observations. Statistica Sinica 28, 1133–1155 (2018)
Kißlinger, A.-L., Stummer, W.: Some decision procedures based on scaled Bregman distance surfaces. In: Nielsen, F., Barbaresco, F. (eds.) GSI 2013. LNCS, vol. 8085, pp. 479–486. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40020-9_52
Kißlinger, A.-L., Stummer, W.: New model search for nonlinear recursive models, regressions and autoregressions. In: Nielsen, F., Barbaresco, F. (eds.) GSI 2015. LNCS, vol. 9389, pp. 693–701. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-25040-3_74
Kißlinger, A.-L., Stummer, W.: Robust statistical engineering by means of scaled Bregman distances. In: Agostinelli, C., Basu, A., Filzmoser, P., Mukherjee, D. (eds.) Recent Advances in Robust Statistics - Theory and Applications, pp. 81–113. Springer, India (2016). https://doi.org/10.1007/978-81-322-3643-6_5
Kißlinger, A.-L., Stummer, W.: A new toolkit for robust distributional change detection. Appl. Stoch. Models Bus. Ind. 34, 682–699 (2018)
Matthys, G., Beirlant, J.: Estimating the extreme value index and high quantiles with exponential regression models. Statistica Sinica 13, 853–880 (2003)
Nielsen, F., Garcia, V.: Statistical exponential families: a digest with flash cards. Preprint, arXiv:0911.4863v2 (2011)
Nielsen, F., Hadjeres, G.: Monte Carlo information-geometric structures. In: Nielsen, F. (ed.) Geometric Structures of Information. SCT, pp. 69–103. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-02520-5_5
Pardo, M.C., Vajda, I.: On asymptotic properties of information-theoretic divergences. IEEE Trans. Inf. Theor. 49(7), 1860–1868 (2003)
Roensch, B., Stummer, W.: 3D insights to some divergences for robust statistics and machine learning. In: Nielsen, F., Barbaresco, F. (eds.) GSI 2017. LNCS, vol. 10589, pp. 460–469. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68445-1_54
Roensch, B., Stummer, W.: Robust estimation by means of scaled Bregman power distances. Part II. Extreme values. In: Nielsen, F., Barbaresco, F. (eds.) GSI 2019. LNCS, vol. 11712, pp. 331–340. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-26980-7_34
Stummer, W.: Some Bregman distances between financial diffusion processes. Proc. Appl. Math. Mech. 7(1), 1050503–1050504 (2007)
Stummer, W., Kißlinger, A.-L.: Some new flexibilizations of Bregman divergences and their asymptotics. In: Nielsen, F., Barbaresco, F. (eds.) GSI 2017. LNCS, vol. 10589, pp. 514–522. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68445-1_60
Stummer, W., Vajda, I.: On Bregman distances and divergences of probability measures. IEEE Trans. Inform. Theory 58(3), 1277–1288 (2012)
Acknowledgement
We are grateful to the five referees for their comments and very useful suggestions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Roensch, B., Stummer, W. (2019). Robust Estimation by Means of Scaled Bregman Power Distances. Part I. Non-homogeneous Data. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2019. Lecture Notes in Computer Science(), vol 11712. Springer, Cham. https://doi.org/10.1007/978-3-030-26980-7_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-26980-7_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26979-1
Online ISBN: 978-3-030-26980-7
eBook Packages: Computer ScienceComputer Science (R0)