×

Generalized linear model for subordinated Lévy processes. (English) Zbl 1496.62127

Summary: Generalized linear models, introduced by Nelder and Wedderburn, allowed to model the regression of normal and nonnormal data. While doing so, the analysis of these models could not be obtained without the explicit form of the variance function. In this paper, we determine the link and variance functions of the natural exponential family generated by the class of subordinated Lévy processes. In this framework, we introduce a class of variance functions that depends on the Lambert function. In this regard, we call it the Lambert class, which covers the variance functions of the natural exponential families generated by the subordinated gamma processes and the subordinated Lévy processes by the Poisson subordinator. Notice that the gamma process subordinated by the Poisson one is excluded from this class. The concept of reciprocity in natural exponential families was given in order to obtain an exponential family from another one. In this context, we get the reciprocal class of the natural exponential family generated by the class of subordinated Lévy processes. It is well known that the variance function represents an essential element for the determination of the quasi-likelihood and deviance functions. Then, we use the expression of our variance function in order to maintain them. This leads us to analyze the proposed generalized linear model. We illustrate some of our models with applications to the daily exchange rate returns of the Tunisian Dinar against the U.S. Dollar and the damage incidents of ships.

MSC:

62J12 Generalized linear models (logistic models)
60G51 Processes with independent increments; Lévy processes
62P10 Applications of statistics to biology and medical sciences; meta analysis
Full Text: DOI

References:

[1] Asmussen, S., Jensen, J. L., & Rojas‐Nandayapa, L. (2014). On the Laplace transform of the lognormal distribution. Methodology and Computing in Applied Probability, 18(2), 441-458. · Zbl 1386.60066
[2] Bar‐Lev, S. K., Bshouty, D., & Enis, P. (1991). Variance functions with meromorphic means. The Annals of Probability, 19(3), 1349-1366. · Zbl 0735.62010
[3] Barndorff‐Nielsen, O. E. (1978). Information and exponential families in statistical theory. Wiley. · Zbl 0387.62011
[4] Barndorff‐Nielsen, O. E. (1997). Normal inverse Gaussian distributions and stochastic volatility modeling. Scandinavian Journal of Statistics, 24, 1-13. · Zbl 0934.62109
[5] Barndorff‐Nielsen, O. E., & Levendorskii, S. Z. (2001). Feller processes of normal inverse Gaussian type. Quantitative Finance, 1(3), 318-331. · Zbl 1405.91582
[6] Barndorff‐Nielsen, O. E., & Schmiegel, J. (2008). Time change, volatility, and turbulence. In A.Sarychev (ed.), A.Shiryaev (ed.), M.Guerra (ed.) and M. R.Grossinho (ed.) (Eds.), Mathematical Control Theory and Finance, pp. 29-53. Springer, Berlin, Heidelberg. · Zbl 1157.60043
[7] Barndorff‐Nielsen, O. E., & Shephard, N. (2001). Normal modified stable processes. Theory of Probability and Mathematical Statistics, 65, 1-19. · Zbl 1026.60058
[8] Barndorff‐Nielsen, O. E., & Shiryaev, A. (2010). Change of time and change of measureAdvanced Series on Statistical Science and Applied Probability (Vol. 13). World Scientific Co. Pte. Ltd. · Zbl 1234.60003
[9] Bertoin, J. (1996). Lévy processes. Cambridge University Press. · Zbl 0861.60003
[10] Bhattacharya, S. K., & Kumar, S. (1986). E‐IG model in life testing. Calcutta Statistical Association Bulletin, 35, 85-90. · Zbl 0619.62090
[11] Bondesson, L., & Steutel, F. (2004). A class of infinitely divisible distributions connected to branching processes and random walks. Journal of Mathematical Analysis and Applications, 295(1), 134-143. · Zbl 1054.60018
[12] Boubacar Maı̈nassara, Y., & Kokonendji, C. C. (2014). On normal stable Tweedie models and power‐generalized variance functions of only one component. Test, 23, 585-606. · Zbl 1308.62111
[13] Casalis, M. (1996). The (2d + 4) simple quadratic natural exponential families on R^d. Annals of Statistics, 24(4), 1828-1854. · Zbl 0867.62042
[14] Chiou, J. M., & Müller, H. G. (1998). Quasi‐likelihood regression with unknown link and variance functions. Journal of the American Statistical Association, 93, 1376-1387. · Zbl 1065.62512
[15] Chiou, J. M., & Müller, H. G. (1999). Nonparametric quasi‐likelihood. Annals of Statistics, 27, 36-64. · Zbl 0978.62056
[16] Clark, P. K. (1973). A subordinated stochastic process model with finite variance for speculative prices. Econometrica, 41(1), 135-155. · Zbl 0308.90011
[17] DasGupta, A. (2011). The exponential family and statistical applications. Probability for Statistics and Machine Learning, 583-612. Springer. · Zbl 1233.62001
[18] Dean, C., Lawless, J. F., & Willmot, G. E. (1989). A mixed Poisson‐inverse Gaussian regression model. The Canadian Journal of Statistics, 17, 171-181. · Zbl 0679.62051
[19] Fan, J., & Chen, J. (1999). One‐step local quasi‐likelihood estimation. Journal of the Royal Statistical Society Series B (Statistical Methodology), 61, 927-943. · Zbl 0940.62039
[20] Fan, J., Heckman, N. E., & Wand, M. P. (1995). Local polynomial kernel regression for generalized linear models and quasi‐likelihood functions. Journal of the American Statistical Association, 90, 141-150. · Zbl 0818.62036
[21] Fiorani, F., Luciano, E., & Semeraro, P. (2010). Single and joint default in a structural model with purely discountinuous asset prices. Quantitative Finance, 10, 249-263. · Zbl 1202.91336
[22] Frangos, N., & Karlis, D. (2004). Modelling losses using an exponential‐inverse Gaussian distribution. Insurance: Mathematics and Economics, 35, 53-67. · Zbl 1054.62127
[23] Ganti, V., Singh, A., Passalacqua, P., & Foufoula‐Georgiou, E. (2009). Subordinated Brownian motion model for sediment transport. Physical Review E, 80, 011111.
[24] Geman, H., Madan, D., & Yor, M. (2001). Time changes for Lévy processes. Mathematical of Finance, 11, 79-96. · Zbl 0983.60082
[25] Gómez‐Déniz, E., Calderín‐Ojeda, E., & Sarabia, J. M. (2013). Gamma‐generalized inverse Gaussian class of distributions with applications. Communications in Statistics‐Theory and Methods, 42(6), 919-933. · Zbl 1347.62029
[26] Hassairi, A., & Louati, M. (2009). Multivariate stable exponential families and Tweedie scale. Journal of Statistical Planning and Inference, 139, 143-158. · Zbl 1149.62043
[27] Hirsa, A., & Madan, D. B. (2003). Pricing American options under variance gamma. Journal of Computational Finance, 7(2), 63-80.
[28] Holla, M. S. (1967). On a Poisson‐inverse Gaussian distribution. Metrika, 11, 115-121. · Zbl 0156.40402
[29] Hougaard, P., Lee, M. L. T., & Whitmore, G. A. (1997). Analysis of overdispersed count data by mixtures of Poisson variables and Poisson processes. Biometrics, 53, 1225-1238. · Zbl 0911.62101
[30] Hudson, H. M. (1978). A natural identity for exponential families with applications in multiparameter estimation. Annals of Statistics, 6(3), 473-484. · Zbl 0391.62006
[31] Jørgensen, B. (1997). The theory of dispersion models. Chapman & Hall. · Zbl 0928.62052
[32] Jørgensen, B. (2013). Generalized linear models. In A. H.El‐Shaarawi (ed.) & W. W.Piegorsch (ed.) (Eds.), Encyclopedia of environmetrics (2nd ed., pp. 1152-1159). Wiley.
[33] Kim, P., Song, R., & Vondraček, Z. (2009). Boundary Harnack principle for subordinate Brownian motions. Stochastic Processes and Their Applications, 119(5), 1601-1631. · Zbl 1166.60046
[34] Kim, P., Song, R., & Vondraček, Z. (2012). Potential theory of subordinate Brownian motions revisited. In J.‐a.Yan (ed.), T.Zhang (ed.), & X.Zhou (ed.) (Eds.), Stochastic Analysis and Applications to Finance (pp. 243-290). World Scientific Publishing. · Zbl 1282.60076
[35] Kokonendji, C. C. (1995). Sur les familles exponentielles naturelles de grand‐Babel. Annales de la Faculté des Sciences de Toulouse, IV, 4, 763-799. · Zbl 0872.62014
[36] Krichene, N. (2008). Subordinated Lévy processes and applications to crude oil options. International Monetary Fund Working Paper, 05/174.
[37] Küchler, U., & Sørensen, M. (1997). Exponential families of stochastic processes. Springer‐Verlag. · Zbl 0882.60012
[38] Kumar, A., Nane, E., & Vellaisamy, P. (2011). Time‐changed Poisson processes. Statistics & Probability Letters, 81, 1899-1910. · Zbl 1227.60063
[39] Leonenko, N. N., Meerschaert, M. M., Schilling, R. L., & Sikorskii, A. (2014). Correlation structure of time‐changed Lévy processes. Communications in Applied and Industrial Mathematics, 6(1), e‐483, 22. · Zbl 1329.60118
[40] Letac, G. (1986). La réciprocité des familles exponentielles naturelles sur R. Comptes rendus de l’Académie des Sciences, Paris Séries I, 303, 61-64. · Zbl 0591.60003
[41] Letac, G. (1989). Le problème de la classification des familles exponentielles naturelles sur R^d ayant une fonction variance quadratique. In H.Heyer (ed.) (Ed.), Probability measures on groups IXLecture Notes in Math (Vol. 1306, pp. 194-215). Springer.
[42] Letac, G. (1991). The classification of natural exponential families by their variances functions. In Proceeding of the 48th session of the international statistical institute (Vol. LIV) Book 3.
[43] Letac, G. (1992). Lecture on natural exponential families and their variance functionsMonografias de Mathematica 50. IMPA. · Zbl 0983.62501
[44] Letac, G., & Mora, M. (1990). Natural real exponential families with cubic variance function. Annals of Statistics, 18, 1-37. · Zbl 0714.62010
[45] Louati, M. (2013). Mixture and Reciprocity of exponential models. Statistics & Probability Letters, 83(2), 452-458. · Zbl 1269.60014
[46] Louati, M., Masmoudi, A., & Mselmi, F. (2015a). Multivariate normal α‐stable exponential families. The Mediterranean Journal of Mathematics, 13, 1307-1323. · Zbl 1375.60045
[47] Louati, M., Masmoudi, A., & Mselmi, F. (2015b). Gamma stopping and drifted stable processesApplied Mathematics in Tunisia, Springer Proceedings in Mathematics and Statistics (Vol. 131, pp. 223-232). Springer.
[48] Louati, M., Masmoudi, A., & Mselmi, F. (2017). Characterizations of multivariate stable processes. The Lithuanian Mathematical Journal, 57(1), 59-68. · Zbl 1370.60091
[49] Louati, M., Masmoudi, A., & Mselmi, F. (2020). The normal tempered stable regression model. Communications in Statistics‐Theory and Methods, 49(2), 500-512. · Zbl 07549047
[50] Madan, D. B., Carr, P., & Chang, E. (1998). The variance gamma process and option pricing. European Finance Review, 2, 79-105. · Zbl 0937.91052
[51] Madan, D. B., & Seneta, E. (1990). The Variance Gamma (V.G.) model for share market returns. Journal of Business, 63(4), 511-524.
[52] Madan, D. B., & Yor, M. (2008). Representing the CGMY and Meixner processes as time changed Brownian motions. The Journal of Computational Finance, 12(1), 27-47.
[53] Maheshwari, A., & Vellaisamy, P. (2019). Fractional Poisson process time‐changed by Lévy subordinator and its inverse. Journal of Theoretical Probability, 32, 1278-1305. · Zbl 1478.60128
[54] Marinelli, C., Rachev, S. T., & Roll, R. (2001). Subordinated exchange rate models: Evidence for heavy tailed distributions and long‐range dependence. Mathematical and Computer Modelling, 34, 955-1001. · Zbl 1006.60011
[55] Mayster, P. (2014). Subordinated Markov branching processes and Lévy processes. Serdica Mathematical Journal, 40, 183-208. · Zbl 1488.60204
[56] Mayster, P. (2018). Consecutive subordination of Poisson processes and Gamma processes. Comptes rendus de l’Académie bulgare des Sciences, 71(6), 735-742. · Zbl 1413.60081
[57] McCullagh, P., & Nelder, J. (1989). Generalized linear models. Chapman & Hall. · Zbl 0744.62098
[58] Morris, C. N. (1982). Natural exponential families with quadratic variance functions. The Annals of Statistics, 10, 65-80. · Zbl 0498.62015
[59] Morris, C. N., & Lock, K. F. (2009). Unifying the named natural exponential families and their relatives. The American Statistician, 63, 247-253.
[60] Mselmi, F., Kokonendji, C. C., Louati, M., & Masmoudi, A. (2018). Generalized variance functions for infinitely divisible mixture distributions. The Mediterranean Journal of Mathematics, 14(4):165, 1-19. · Zbl 1401.62081
[61] Mselmi, F. (2018a). Lévy processes time‐changed by the first‐exit time of the inverse Gaussian subordinator. Filomat, 32(7), 2545-2552. · Zbl 1499.60147
[62] Mselmi, F. (2018b). Characterization of the inverse stable subordinator. Statistics & Probability Letters, 140, 37-43. · Zbl 1391.60109
[63] Mselmi, F. (2018c). The stable processes on symmetric matrices. The Arab Journal of Mathematical Sciences, 24(1), 63-69. · Zbl 1387.60081
[64] Mselmi, F. (2021). Approximation of the quasi‐deviance function for the time‐changed Lévy processes by the first‐exit time of the inverse Gaussian subordinator. Stat. https://doi.org/10.1002/sta4.362 · Zbl 07851302 · doi:10.1002/sta4.362
[65] Nelder, J., & Wedderburn, R. W. M. (1972). Generalized linear models. Journal of the Royal Statistical Society: Series A (Statistics in Society), 135(3), 370-384.
[66] Ord, J. K., & Whitmore, G. A. (1986). The Poisson‐inverse Gaussian distribution as a model for species abundance. Communications in Statistics‐Theory and Methods, 15, 853-871. · Zbl 0603.62113
[67] Pakes, A. G. (2011). Lambert’s W, infinite divisibility and Poisson mixtures. Journal of Mathematical Analysis and Applications, 378(2), 480-492. · Zbl 1223.60016
[68] Pierce, D. A., & Schafer, D. W. (1986). Residuals in generalized linear models. Journal of the American Statistical Association, 81, 977-986. · Zbl 0644.62076
[69] Rigby, R. A., Stasinopoulos, D. M., & Akantziliotou, C. (2008). A framework for modelling overdispersed count data, including the Poisson‐shifted generalized inverse Gaussian distribution. Computational Statistics & Data Analysis, 53, 381-393. · Zbl 1231.62019
[70] Rydberg, T. (1996). The normal inverse Gaussian Lévy Process: simulation and approximation. Communications in Statistics Stochastic Models, 13, 887-910. · Zbl 0899.60036
[71] Sato, K. I. (1999). Lévy processes and infinitely divisible distributions. Cambridge University Press. · Zbl 0973.60001
[72] Song, R., & Vondraček, Z. (2003). Potential theory of subordinate killed Brownian motion in a domain. Probability Theory and Related Fields, 125, 578-592. · Zbl 1022.60078
[73] Teugels, J. L. (1972). A note on Poisson‐subordination. The Annals of Mathematical Statistics, 43(2), 676-680. · Zbl 0238.60096
[74] Tremblay, L. (1992). Using the Poisson inverse Gaussian in bonus‐malus systems. Astin Bulletin, 22, 97-106.
[75] Vinogradov, V. (2011). On Kendall‐Ressel and related distributions. Statistics & Probability Letters, 81, 1493-1501. · Zbl 1232.60016
[76] Vinogradov, V. (2013). Some utilizations of Lambert W function in distribution theory. Communications in Statistics‐Theory and Methods, 42, 2025-2043. · Zbl 1277.60035
[77] Wedderburn, R. W. M. (1974). Quasi‐likelihood functions, generalized linear models, and the Gauss‐Newton method. Biometrika, 61(3), 439-447. · Zbl 0292.62050
[78] Willmot, G. E. (1987). The Poisson‐inverse Gaussian distribution as an alternative to the negative binomial. Scandinavian Actuarial Journal, 1987(3‐4), 113-127.
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.