×

On the mean value parametrization of natural exponential families – a revisited review. (English) Zbl 1387.60028

Summary: It is well known that any natural exponential family (NEF) is characterized by its variance function on its mean domain, often much simpler than the corresponding generating probability measures. The mean value parametrization appeared to be crucial in some statistical theory, like in generalized linear models, exponential dispersion models and Bayesian framework. The main aim of the paper is to expose the mean value parametrization for possible statistical applications. The paper presents an overview of the mean value parametrization and of the characterization property of the variance function for NEF’s. In particular it introduces the relationships existing between the NEF’s generating measure, Laplace transform and variance function as well as some supplemental results concerning the mean value representation. Some classes of polynomial variance functions are revisited for illustration. The corresponding NEF’s of such classes are generated by counting probabilities on the nonnegative integers and provide Poisson-overdispersed competitors to the homogeneous Poisson distribution.

MSC:

60E10 Characteristic functions; other transforms
62E10 Characterization and structure theory of statistical distributions
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Y. Awad, S. K. Bar-Lev, and U. Makov, A New Class of Counting Distributions Embedded in the Lee-Carter Model forMortality Projections: A Bayesian Approach, Techn. Rep. (Actuarial Research Center, Univ. of Haifa, Israel, 2016) (in press).
[2] S. K. Bar-Lev, “Discussion on paper by B. Jørgensen ‘Exponential dispersion models’,” J. Roy. Statist. Soc., Ser. B 49, 153-154 (1987).
[3] S. K. Bar-Lev, B. Boukai, and I. Kleiner, “The Kendal-Ressel Exponential Dispersion Model: Some Statistical Aspects and Estimation”, Int. J. Statist. and Probab. 5 (3), 32-41 (2016). · doi:10.5539/ijsp.v5n3p32
[4] S. K. Bar-Lev and D. Bshouty, “A Class of Infinitely Divisible Variance Functions with an Application to the Polynomial Case”, Probab. and Statist. Lett. 10, 377-379 (1990). · Zbl 0721.62017 · doi:10.1016/0167-7152(90)90017-2
[5] S. K. Bar-Lev, D. Bshouty, and P. Enis, “Variance Functions with Meromorphic Means”, Ann. Probab. 19, 1349-1366 (1991). · Zbl 0735.62010 · doi:10.1214/aop/1176990348
[6] S. K. Bar-Lev, D. Bshouty, and P. Enis, “On Polynomial Variance Functions”, Probab. Theory and Rel. Fields 94, 69-82 (1991). · Zbl 0766.62006 · doi:10.1007/BF01222510
[7] S. K. Bar-Lev, D. Bshouty, P. Enis, and A. Y. Ohayon, “Compositions and Products of Infinitely Divisible Variance Functions”, Scandinavian J. Statist. 19, 83-89 (1992). · Zbl 0753.60023
[8] S. K. Bar-Lev, D. Bshouty, P. Grünwald, and P. Harremoës, “Jeffreys versus Shtarkov Distributions Associated with Some Natural Exponential Families”, Statist. Methodology 7, 638-643 (2010). · Zbl 1463.62024 · doi:10.1016/j.stamet.2010.06.001
[9] S. K. Bar-Lev, D. Bshouty, and Z. Landsman, “Second Order Minimax Estimation of the Mean”, J. Statist. Planning and Inference 140, 3282-3294 (2010). · Zbl 1327.62038 · doi:10.1016/j.jspi.2010.04.056
[10] S. K. Bar-Lev and P. Enis, “Reproducibility and Natural Exponential Families with Power Variance Functions”, Ann. Statist. 14, 1507-1522 (1986). · Zbl 0657.62016 · doi:10.1214/aos/1176350173
[11] S. K. Bar-Lev and G. Letac, “Increasing Hazard Rate of Mixtures for Natural Exponential Families”, Advances in Appl. Probab. 44, 373-390 (2009). · Zbl 1246.60029 · doi:10.1017/S0001867800005644
[12] S. K. Bar-Lev and Z. Landsman, “Exponential Dispersion Models: Second-Order Minimax Estimation of the Mean for Unknown Dispersion Parameter”, J. Statist. Planning and Inference 136, 3837-3851 (2006). · Zbl 1104.62004 · doi:10.1016/j.jspi.2005.05.003
[13] O. E. Barndorff-Nielsen, Information and Exponential Families in Statistical Theory (Wiley, New York, 1978). · Zbl 0387.62011
[14] J. Castillo and M. Pérez-Casany, “Overdispersed and Underdispersed Poisson Generalizations”, J. Statist. Planning and Inference 134, 486-500 (2005). · Zbl 1121.62015 · doi:10.1016/j.jspi.2004.04.019
[15] A. Delwarde, M. Denuit, and C. Partrat, “Negative Binomial Version of the Lee-Carter Model for Mortality Forecasting”, Appl. StochasticModels in Business and Industry 23 (5), 385-401 (2007). · Zbl 1150.91426 · doi:10.1002/asmb.679
[16] P. K. Dunn and G. K. Smith, “Series Evaluation of Tweedie Exponential Dispersion Densities”, Statistics and Computing 15, 267-280 (2005). · doi:10.1007/s11222-005-4070-y
[17] P. K. Dunn and G. K. Smith, “Evaluation of Tweedie Exponential Dispersion Model Densities by Fourier Inversion”, Statistics and Computing 18, 73-86 (2008). · doi:10.1007/s11222-007-9039-6
[18] I. S. Gradshteyn and I. M. Ryzhik, Tables of Integrals, Series and Products (seventh edition) (Elsevier and Academic Press, New York, 2007). · Zbl 1208.65001
[19] S. Haberman and A. Renshaw, “A Comparative Study of Parametric Mortality Projection Models”, Insurance: Mathematics and Economics 48 (1), 35-55 (2011).
[20] D. B. Hall and K. S. Berenhaut, “Score Tests for Heterogeneity and Overdispersion in Zero-Inflated Poisson and Binomial Regression Models”, Canadian J. Statist. 30, 1-16 (2002). · Zbl 1040.62062 · doi:10.2307/3316145
[21] J. Hinde and C. G. B. Demétrio, “Overdispersion: Models and Estimation”, Comput. Statist. and Data Analysis 27, 151-170 (1998). · Zbl 1042.62578 · doi:10.1016/S0167-9473(98)00007-3
[22] P. Hougaard, K.-L. T. Lee, and G. A. Whitmore, “Analysis of Overdispersed Count Data by Mixtures of Poisson Variables and Poisson Processes”, Biometrics 53, 1225-1238 (1997). · Zbl 0911.62101 · doi:10.2307/2533492
[23] N. L. Johnson, S. Kotz, and A. W. Kemp, Univariate Discrete Distributions, 2nd ed. (Wiley, New York, 1992). · Zbl 0773.62007
[24] B. Jørgensen, “Exponential Dispersion Models (with Discussion)”, J. Roy. Statist. Soc., Ser. B 49, 127-162 (1987). · Zbl 0662.62078
[25] Jørgensen, B., The Theory of Exponential Dispersion Models (1997), London · Zbl 0928.62052
[26] C. C. Kokonendji, S. Dossou-Gbété, and C. G. B. Demétrio, “Some Discrete Exponential Dispersion Models: Poisson-Tweedie and Hinde-Demétrio Classes”, Statist. and Operations Research Transactions 28, 201-214 (2004). · Zbl 1274.62122
[27] C. C. Kokonendji, C. G. B. Demétrio, and S. S. Zocchi, “On Hinde-Demétrio Regression Models for Overdispersed Count Data”, Statist. Methodology 4, 277-291, (2007). · Zbl 1248.62126 · doi:10.1016/j.stamet.2006.10.001
[28] C. C. Kokonendji and M. Khoudar, “On Strict Arcsine Distribution”, Commun. Statist.-Theory and Methods 33, 993-1006 (2004). · Zbl 1114.62313 · doi:10.1081/STA-120029820
[29] C. C. Kokonendji and M. Khoudar, “On LévyMeasures for Infinitely DivisibleNatural Exponential Families”, Statist. and Probab. Lett. 76, 1364-1368 (2006). · Zbl 1110.60008 · doi:10.1016/j.spl.2006.02.006
[30] C. C. Kokonendji and D. Malouche, “A Property of Count Distributions in the Hinde-Demétrio Family”, Commun. Statist.-Theory and Methods 37, 1823-1834 (2008). · Zbl 1318.62037 · doi:10.1080/03610920701809266
[31] R. D. Lee and L. Carter, “Modeling and Forecasting the Time Series of US Mortality”, J. Amer. Statist. Assoc. 87, 659-671 (1992). · Zbl 1351.62186
[32] Letac, G., Lectures on Natural Exponential Families and Their Variance Functions (1992), Rio de Janeiro · Zbl 0983.62501
[33] Letac, G.; Podolskij, M. (ed.); Stelzer, R. (ed.); Thorbjornsen, S. (ed.); Veraat, A. E. D. (ed.), Associated Natural Exponential Families and Elliptic Functions (2016)
[34] G. Letac and M. Mora, “Natural Real Exponential Families with Cubic Variance Functions”, Ann. Statist. 18, 1-37 (1990). · Zbl 0714.62010 · doi:10.1214/aos/1176347491
[35] E. Lukacs, Characteristic Functions, 2nd ed. (Hafner, New York, 1970). · Zbl 0201.20404
[36] E. Lukacs, Developments in Characteristic Functions Theory (Griffin, London, 1983). · Zbl 0515.60022
[37] C. N. Morris, “Natural Exponential Families with Quadratic Variance Functions”, Ann. Statist. 10, 65-80 (1982). · Zbl 0498.62015 · doi:10.1214/aos/1176345690
[38] C. N. Morris, “Natural Exponential Families with Quadratic Variance Functions: Statistical Theory”, Ann. Statist. 11, 515-529 (1983). · Zbl 0521.62014 · doi:10.1214/aos/1176346158
[39] J. A. Nelder and R. W. M. Wedderburn, “Generalized Linear Models”, J. Roy. Statist. Soc., Ser. A 135, 370-384 (1972). · doi:10.2307/2344614
[40] R. S. Pimentel, M. Niewiadomska-Bugaj, and J.-C. Wang, “Association of Zero-Inflated Continuous Variables”, Statist. and Probab. Lett. 96, 61-67 (2015). · Zbl 1314.62132 · doi:10.1016/j.spl.2014.09.002
[41] N. U. Prabhu, Queues and Inventories: A Study of Basic Stochastic Processes (Wiley, New York, 1965). · Zbl 0131.16904
[42] A. E. Renshaw and S. Haberman, “A Cohort-Based Extension to the Lee-Carter Model for Mortality Reduction Factors”, Insurance:Mathematics and Economics 38, 556-570 (2006). · Zbl 1168.91418
[43] Ridout, M.; Demétrio, C. G. B.; Hinde, J., Models for Count Data with Many Zeros, 179-192 (1998)
[44] G. K. Smyth and B. Jørgensen, “Fitting Tweedie’s Compound Poisson Model to Insurance Claims Data: Dispersion Modelling”, Astin Bulletin 32, 143-157 (2002). · Zbl 1094.91514 · doi:10.2143/AST.32.1.1020
[45] Tweedie, M. C. K.; Ghosh, J. K. (ed.); Roy, J. (ed.), An Index Which Distinguishes between Some Important Exponential Families, 579-604 (1984), Calcutta
[46] V. Vinogradov, R. B. Paris, and O. Yanushkevichiene, “New Properties for Members of the Power-Variance Family. I”, Lithuanian Math. J. 52, 444-461 (2012). · Zbl 1284.60040 · doi:10.1007/s10986-012-9186-0
[47] V. Vinogradov, R. B. Paris, and O. Yanushkevichiene, “New Properties for Members of the Power-Variance Family. II”, Lithuanian Math. J. 53, 103-120 (2013). · Zbl 1277.60036 · doi:10.1007/s10986-013-9197-5
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.