Maximum L\(q\)-likelihood estimation. (English) Zbl 1183.62033

Summary: The maximum L\(q\)-likelihood estimator (ML\(q\)E), a new parameter estimator based on nonextensive entropy [J. Havrda and F. Charvat, Kybernetika 3, 30–35 (1967; Zbl 0178.22401)] is introduced. The properties of the ML\(q\)E are studied via asymptotic analysis and computer simulations. The behavior of the ML\(q\)E is characterized by the degree of distortion \(q\) applied to the assumed model. When \(q\) is properly chosen for small and moderate sample sizes, the ML\(q\)E can successfully trade bias for precision, resulting in a substantial reduction of the mean squared error. When the sample size is large and \(q\) tends to 1, a necessary and sufficient condition to ensure proper asymptotic normality and efficiency of ML\(q\)E is established.


62F10 Point estimation
60F05 Central limit and other weak theorems
62B10 Statistical aspects of information-theoretic topics
62G32 Statistics of extreme values; tail inference
65C60 Computational problems in statistics (MSC2010)
62F12 Asymptotic properties of parametric estimators


Zbl 0178.22401
Full Text: DOI arXiv


[1] Abe, S. (2003). Geometry of escort distributions. Phys. Rev. E 68 031101.
[2] Aczél, J. D. and Daróczy, Z. (1975). On measures of information and their characterizations. Math. Sci. Eng. 115 . Academic Press, New York-London. · Zbl 0345.94022
[3] Akaike, H. (1973). Information theory and an extension of the likelihood principle. In 2nd International Symposium of Information Theory 267-281. Akad. Kiadó, Budapest. · Zbl 0283.62006
[4] Altun, Y. and Smola, A. (2006). Unifying divergence minimization and statistical inference via convex duality. In Learning Theory. Lecture Notes in Computer Science 4005 139-153. Springer, Berlin. · Zbl 1143.68513
[5] Barron, A., Rissanen, J. and Yu, B. (1998). The minimum description length principle in coding and modeling. IEEE Trans. Inform. Theory 44 2743-2760. · Zbl 0933.94013
[6] Basu, A. Harris, I. R., Hjort, N. L. and Jones, M. C. (1998). Robust and efficient estimation by minimising a density power divergence. Biometrika 85 549-559. JSTOR: · Zbl 0926.62021
[7] Beck, C. and Schlögl, F. (1993). Thermodynamics of Chaotic Systems: An Introduction . Cambridge Univ. Press, Cambridge. · Zbl 0847.58051
[8] Choi, E., Hall, P. and Presnell, B. (2000). Rendering parametric procedures more robust by empirically tilting the model. Biometrika 87 453-465. JSTOR: · Zbl 0948.62022
[9] Cover, T. M. and Thomas, J. A. (2006). Elements of Information Theory . Wiley, New York. · Zbl 1140.94001
[10] Daniels, H. E. (1997). Saddlepoint approximations in statistics (Pkg: P171-200). In Breakthroughs in Statistics (S. Kotz and N. L. Johnson, eds.) 3 177-200. Springer, New York.
[11] Ferguson, T. S. (1996). A Course in Large Sample Theory . Chapman & Hall, London. · Zbl 0871.62002
[12] Ferrari, D. and Paterlini, S. (2007). The maximum Lq-likelihood method: An application to extreme quantile estimation in finance. Methodol. Comput. Appl. Probab. 11 3-19. · Zbl 1293.62064
[13] Field, C. and Ronchetti, E. (1990). Small Sample Asymptotics . IMS, Hayward, CA. · Zbl 0742.62016
[14] Gell-Mann, M., ed. (2004). Nonextensive Entropy, Interdisciplinary Applications . Oxford Univ. Press, New York. · Zbl 1127.82004
[15] Goldfarb, D. (1970). A family of variable-metric method derived by variational means. Math. Comp. 24 23-26. JSTOR: · Zbl 0196.18002
[16] Havrda, J. and Charvát, F. (1967). Quantification method of classification processes: Concept of structural entropy. Kibernetika 3 30-35. · Zbl 0178.22401
[17] Huang, J. Z., Liu, N., Pourahmadi, M. and Liu, L. (2006). Covariance matrix selection and estimation via penalised normal likelihood. Biometrika 93 85-98. · Zbl 1152.62346
[18] Huber, P. J. (1981). Robust Statistics . Wiley, New York. · Zbl 0536.62025
[19] Jaynes, E. T. (1957). Information theory and statistical mechanics. Phys. Rev. 106 620. · Zbl 0084.43701
[20] Jaynes, E. T. (1957). Information theory and statistical mechanics II. Phys. Rev. 108 171. · Zbl 0084.43701
[21] Kullback, S. (1959). Information Theory and Statistics . Wiley, New York. · Zbl 0088.10406
[22] Kullback, S. and Leibler, R. A. (1951). On information and sufficiency. Ann. Math. Statistics 22 79-86. · Zbl 0042.38403
[23] Lehmann, E. L. and Casella, G. (1998). Theory of Point Estimation . Springer, New York. · Zbl 0916.62017
[24] Magnus, J. R. and Neudecker, H. (1979). The commutation matrix: Some properties and applications. Ann. Statist. 7 381-394. · Zbl 0414.62040
[25] McCulloch, C. E. (1982). Symmetric matrix derivatives with applications. J. Amer. Statist. Assoc. 77 679-682. JSTOR: · Zbl 0503.62052
[26] Naudts, J. (2004). Estimators, escort probabilities, and phi-exponential families in statistical physics. J. Inequal. Pure Appl. Math. 5 102. · Zbl 1076.62027
[27] Rényi, A. (1961). On measures of entropy and information. In Proc. 4th Berkeley Sympos. Math. Statist. and Prob. 1 547-461. Univ. California Press, Berkeley.
[28] Shannon, C. E. (1948). A mathematical theory of communication. Bell System Tech. J. 27 379-423. · Zbl 1154.94303
[29] Tsallis, C. (1988). Possible generalization of Boltzmann-Gibbs statistics. J. Statist. Phys. 52 479-487. · Zbl 1082.82501
[30] Tsallis, C., Mendes, R. S. and Plastino, A. R. (1998). The role of constraints within generalized nonextensive statistics. Physica A: Statistical and Theoretical Physics 261 534-554.
[31] van der Vaart, A. W. (1998). Asymptotic Statistics . Cambridge Univ. Press, Cambridge. · Zbl 0910.62001
[32] Wang, X., van Eeden, C. and Zidek, J. V. (2004). Asymptotic properties of maximum weighted likelihood estimators. J. Statist. Plann. Inference 119 37-54. · Zbl 1041.62020
[33] Windham, M. P. (1995). Robustifying model fitting. J. Roy. Statist. Soc. Ser. B 57 599-609. JSTOR: · Zbl 0827.62030
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.