Abstract
We introduce a class of two-parameter discrete dispersion models, obtained by combining convolution with a factorial tilting operation, similar to exponential dispersion models which combine convolution and exponential tilting. The equidispersed Poisson model has a special place in this approach, whereas several overdispersed discrete distributions, such as the Neyman Type A, Pólya–Aeppli, negative binomial and Poisson-inverse Gaussian, turn out to be Poisson–Tweedie factorial dispersion models with power dispersion functions, analogous to ordinary Tweedie exponential dispersion models with power variance functions. Using the factorial cumulant generating function as tool, we introduce a dilation operation as a discrete analogue of scaling, generalizing binomial thinning. The Poisson–Tweedie factorial dispersion models are closed under dilation, which in turn leads to a Poisson–Tweedie asymptotic framework where Poisson–Tweedie models appear as dilation limits. This unifies many discrete convergence results and leads to Poisson and Hermite convergence results, similar to the law of large numbers and the central limit theorem, respectively. The dilation operator also leads to a duality transformation which in some cases transforms overdispersion into underdispersion and vice versa. Finally, we consider the multivariate factorial cumulant generating function, and introduce a multivariate notion of over- and underdispersion, and a multivariate zero inflation index.
Similar content being viewed by others
References
Barreto-Souza, W., Bourguignon, M.: A skew INAR(1) process on \(\mathbb{Z}\). AStA Adv. Stat. Anal. 99, 189–208 (2015)
Bryc, W.: Free exponential families as kernel families. Demonstr. Math. XLII, 657–672 (2009)
Dobbie, M.J., Welsh, A.H.: Models for zero-inflated count data using the Neyman type A distribution. Stat. Model. 1, 65–80 (2001)
El-Shaarawi, A.H., Zhu, R., Joe, H.: Modelling species abundance using the Poisson-Tweedie family. Environmetrics 22, 152–164 (2011)
Giles, D.E.: Hermite regression analysis of multi-modal count data. Econ. Bull. 30, 2936–2945 (2010)
Grandell, J.: Mixed Poisson Processes. Chapman & Hall, London (1997)
Harremoës, P., Johnson, O., Kontoyiannis, I.: Thinning, entropy, and the law of thin numbers. IEEE Trans. Inf. Theory 56, 4228–4244 (2010)
Hougaard, P., Lee, M-L.T., Whitmore, G.A.: Analysis of overdispersed count data by mixtures of Poisson variables and Poisson processes. Biometrics 53, 1225–1238 (1997)
Jensen, S.T., Nielsen, B.: On convergence of multivariate Laplace transforms. Statist. Probab. Lett. 33, 125–128 (1997)
Johnson, N.L., Kotz, S., Balakrishnan, N.: Discrete Multivariate Distributions. Wiley, New York (1997)
Johnson, N.L., Kemp, A.W., Kotz, S.: Univariate Discrete Distributions, 3rd edn. Wiley, Hoboken (2005)
Jørgensen, B.: The Theory of Dispersion Models. Chapman & Hall, London (1997)
Jørgensen, B., Kokonendji, C.C.: Dispersion models for geometric sums. Braz. J. Probab. Statist. 25, 263–293 (2011)
Jørgensen, B., Martínez, J.R.: Multivariate exponential dispersion models. In: Kollo, T. (ed.) Multivariate Statistics: Theory and Applications. Proceedings of the IX Tartu Conference on Multivariate Statistics & XX International Workshop on Matrices and Statistics, pp. 73–98. World Scientific, Singapore (2013)
Jørgensen, B., Martínez, J.R., Tsao, M.: Asymptotic behaviour of the variance function. Scand. J. Stat. 21, 223–243 (1994)
Jørgensen, B., Goegebeur, Y., Martínez, J.R.: Dispersion models for extremes. Extremes 13, 399–437 (2010)
Jørgensen, B., Demétrio, C.G.B., Kristensen, E., Banta, G.T., Petersen, H.C., Delefosse, M.: Bias-corrected Pearson estimating functions for Taylor’s power law applied to benthic macrofauna data. Stat. Probab. Lett. 81, 749–758 (2011)
Kalashnikov, V.: Geometric Sums: Bounds for Rare Events with Applications. Kluwer Academic Publishers, Dordrecht (1997)
Karlis, D., Xekalaki, E.: Mixed poisson distributions. Int. Stat. Rev. 73, 35–58 (2005)
Kemp, A.W.: Characterizations of a discrete normal distribution. J. Stat. Plan. Inf. 63, 223–229 (1997)
Kemp, C.D., Kemp, A.W.: Some properties of the ‘Hermite’ distribution. Biometrika 52, 381–394 (1965)
Khatri, C.G.: On certain properties of power-series distributions. Biometrika 46, 486–490 (1959)
Kokonendji, C.C., Pérez-Casany, M.: A note on weighted count distributions. J. Stat. Theory Appl. 11, 337–352 (2012)
Kokonendji, C.C., Dossou-Gbété, S., Demétrio, C.G.B.: Some discrete exponential dispersion models: Poisson-Tweedie and Hinde-Demétrio classes. Stat Operat Res Trans (SORT) 28, 201–214 (2004)
Kokonendji, C.C., Mizère, D., Balakrishnan, N.: Connections of the Poisson weight function to overdispersion and underdispersion. J. Stat. Plan. Inf. 138, 1287–1296 (2008)
Massé, J.-C., Theodorescu, R.: Neyman type A distribution revisited. Stat. Neerl. 59, 206–213 (2005)
McKenzie, E.: Some simple models for discrete variates time series. Water Resour. Bull. 21, 645–650 (1985)
Mora, M.: La convergence des fonctions variance des familles exponentielles naturelles. Ann. Fac. Sci. Toulouse 11(5), 105–120 (1990)
Pistone, G., Wynn, H.P.: Finitely generated cumulants. Stat. Sinica 9, 1029–1052 (1999)
Puig, P.: Characterizing additively closed discrete models by a property of their maximum likelihood estimators, with an application to generalized Hermite distributions. J. Am. Stat. Assoc. 98, 687–692 (2003)
Puig, P., Barquinero, F.: An application of compound Poisson modelling to biological dosimetry. Proc. R. Soc. A 467, 897–910 (2011)
Puig, P., Valero, J.: Count data distributions: some characterizations with applications. J. Am. Stat. Assoc. 101, 332–340 (2006)
Puig, P., Valero, J.: Characterization of count data distributions involving additivity and binomial subsampling. Bernoulli 13, 544–555 (2007)
Ristić, M.M., Bakouch, H.S., Nastić, A.S.: A new geometric first-order integer-valued autoregressive (NGINAR(1)) process. J. Stat. Plan. Inference 139, 2218–2226 (2009)
Roy, D.: The discrete normal distribution. Commun. Stat. Theory Methods 32, 1871–1883 (2003)
Rudin, W.: Principles of Mathematical Analysis, 3rd edn. McGraw-Hill, New York (1976)
Sellers, K.F., Borle, S., Shmueli, G.: The COM-Poisson model for count data: a survey of methods and applications. Appl. Stoch. Models Bus. Ind. 28, 104–116 (2012)
Shmueli, G., Minka, T.P., Kadane, J.P., Borle, S., Boatwright, P.: A useful distribution for fitting discrete data: revival of the Conway-Maxwell-Poisson distribution. Appl. Stat. 54, 127–142 (2005)
Steutel, F.W., van Harn, K.: Discrete analogues of self-decomposability and stability. Ann. Probab. 7, 893–899 (1979)
Taylor, L.R., Taylor, R.A.J.: Aggregation, migration and population mechanics. Nature 265, 415–421 (1977)
Thedéen, T.: The inverses of thinned point processes. Research report 1986:1. Department of Statistics, University of Stockholm (1986)
Tweedie, M.C.K.: An index which distinguishes between some important exponential families. In: Ghosh, J.K., Roy, J. (eds.) Statistics: Applications and New Directions. Proceedings of the Indian Statistical Institute Golden Jubilee International Conference, pp. 579–604. Indian Statistical Institute, Calcutta (1984)
Weiß, C.H.: Thinning operations for modeling time series of counts—a survey. AStA Adv. Stat. Anal. 92, 319–341 (2008)
Willmot, G.E.: The Poisson-inverse Gaussian distribution as an alternative to the negative binomial. Scand. Actuar. J. 1987, 113–127 (1987)
Wimmer, G., Altmann, G.: Thesaurus of Univariate Discrete Probability Distributions. STAMM Verlag, Essen (1999)
Wiuf, C., Stumpf, M.P.H.: Binomial subsampling. Proc. R. Soc. A 462, 1181–1195 (2006)
Acknowledgments
We are grateful to Christian Weiß and two anonymous referees for useful comments on a previous version of the paper.
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix A: Exponential dispersion models
In this appendix, we summarize some relevant facts about exponential dispersion models and Tweedie models. An exponential dispersion model \(\mathrm {ED}(\mu ,\gamma )\) with mean \(\mu \in \Omega \), dispersion parameter \(\gamma >0\) and unit variance function \(V(\mu )\) has PDF of the form
where the unit deviance function \(\mathrm{d}(y;\mu )\) is defined by
The model (6.1) is, for each known value of \(\gamma \), a natural exponential family with variance function \(\gamma V(\mu )\). Hence, the function \(a(y;\gamma )\) may be determined by Fourier inversion from the CGF, which may in turn be obtained from \(V\). The model \(\mathrm {ED}(\mu ,\gamma )\) satisfies the following reproductive property:
where \(\overline{Y}_{n}\) is the average of \(Y_{1},\ldots ,Y_{n}\), which are i.i.d. from \(\mathrm {ED}(\mu ,\gamma )\).
The Tweedie exponential dispersion model \(\mathrm {Tw}_{p}(\mu ,\gamma )\) has mean \(\mu \) and unit variance function
The domain for \(\mu \) is either \(\Omega _{0}=R\) or \(\Omega _{p}=R_{+}\) for \( p\ne 0\). Tweedie models satisfy the scaling property
Conventional Tweedie asymptotics (Jørgensen et al. 1994) have the following form. If \(\mathtt {\mathrm {ED}}(\mu ,\gamma )\) with unit variance function \(V(\mu )\) satisfies
then
respectively. The proof is based on convergence of the variance function on the left-hand side of (6.4),
applying Mora’s (1990) convergence theorem. The case \( c^{2-p}\rightarrow \infty \) requires the model \(\mathtt {\mathrm {ED}}(\mu ,\gamma )\) to be infinite divisible. This result implies a Tweedie approximation, by means of (6.3)
In some cases, we have a large-sample interpretation of Tweedie convergence. Let us consider the average \(\bar{Y}_{n}\) with distribution (6.2). Then for \(p\ne 2\) we obtain
We interpret this result as saying that the scaled and exponentially tilted average \(\bar{Y}_{n}\) converges to a Tweedie distribution as \(n\rightarrow \infty \).
Appendix B: Proof of Theorem 4.1
Consider a sequence of factorial tilting families \(\mathrm {FT}_{n}(\mu )\) with local dispersion functions \(v_{n}\) having domain \(\Psi _{n}\) and FCGF \( C_{n}\) satisfying the conditions of Theorem 4.1. The idea of the proof is to obtain the FCGF derivative \(\dot{C}\) from the limiting dispersion function \(v\), and in turn use the uniform convergence to show convergence of the sequence \(C_{n}\).
We begin by considering the nonzero case, where \(v(\mu )\ne 0\) for \(\mu \in \Psi _{0}\). Let \(K\) be a given compact subinterval of \(\Psi _{0}\). By assumption \(\Psi _{0}\subseteq \mathrm {int}\left( \lim \Psi _{n}\right) \), so we may assume that \(K\subseteq \Psi _{n}\) from some \(n_{0}\) on. We only need to consider \(n>n_{0}\) from now on. Fix a \(\mu _{0}\in \mathrm {int}\,K\). Let \(\psi _{n}=\dot{C}_{n}^{-1}\) denote the inverse FCGF derivative defined by \(\dot{\psi }_{n}\left( \mu \right) =1/v_{n}(\mu )\) on \(\Psi _{n}\) and \( \psi _{n}\left( \mu _{0}\right) =0\). Let \(\dot{C}_{n},\, C_{n}\), etc., denote the quantities associated with this parametrization. Similarly, define \(\psi :\Psi _{0}\rightarrow \mathbb {R}\) by \(\dot{\psi }\left( \mu \right) =1/v(\mu ) \) on \(\Psi _{0}\) and \(\psi (\mu _{0})=0\). Then for \(\mu \in K\)
By the uniform convergence of \(v_{n}(\mu )\) to \(v(\mu )\) on \(K\), it follows that \(\left\{ v_{n}(\mu )\right\} \) is uniformly bounded on \(K\). Since \( v(\mu )\) is bounded on \(K\), it follows from (6.5) and from the uniform convergence of \(v_{n}\) that \(\dot{\psi }_{n}\left( \mu \right) \rightarrow \dot{\psi }\left( \mu \right) \) uniformly on \(K\). This and the fact that \(\psi _{n}\left( \mu _{0}\right) =\psi (\mu _{0})\) for all \(n\) implies, by a result from Rudin (1976, Theorem 7.17), that \(\psi _{n}\left( \mu \right) \rightarrow \psi \left( \mu \right) \) uniformly on \(K\). Since \(K\) was arbitrary, we have \(\psi _{n}\left( \mu \right) \rightarrow \psi \left( \mu \right) \) for all \(\mu \in \Psi _{0}\).
Let \(I_{n}=\psi _{n}\left( \Psi _{n}\right) \) and \(I_{0}=\psi (\Psi _{0})\subseteq \mathrm {int}\left( \lim I_{n}\right) \). Let \(J=\psi (K)\subseteq I_{0}\) and \(J_{n}=\psi _{n}(K)\subseteq I_{n}\). Define \(\dot{C} :I_{0}\rightarrow \Psi _{0}\) by \(\dot{C}(y)=\psi ^{-1}(y)\). Since \(\psi \) is strictly monotone and differentiable, the same is the case for \(\dot{C}\). Let \(\mu \in K\) be given and let \(y=\psi (\mu )\in J\) and \(y_{n}=\psi _{n}(\mu )\in J_{n}\). Since \(v_{n}(\mu )\) is uniformly bounded on \(K\), there exists an \(M>0\) such that \(\left| v_{n}(\mu )\right| \le M\) for all \(n\) and \(\mu \in K\). It follows that \(\left| \ddot{C}_{n}(y)\right| =\left| v_{n}\left( \dot{C}_{n}(y)\right) \right| \le M\) for all \( y\in J\) due to the fact that \(J\subseteq J_{n}\) for \(n\) large enough. Since \(\mu =\dot{C}(y)=\dot{C}_{n}(y_{n})\) we find, using the mean value theorem, that
This implies that \(\dot{C}_{n}(y)\rightarrow \dot{C}(y)\) uniformly in \(y\in J \). Since \(C(0)=C_{n}(0)\) for all \(n\), it follows by similar arguments as above that \(C_{n}(y)\rightarrow C(y)\) uniformly on \(J\). We conclude from the convergence of the sequence of MGFs \(\exp \left[ C_{n}\left( e^{s}-1\right) \right] \rightarrow \exp \left[ C\left( e^{s}-1\right) \right] \) for \(s\in \log \left( J+1\right) \) that the sequence of distributions \(\mathrm {FT}_{n}(\mu _{0})\) converges weakly to a probability measure \(P\) with FCGF \(C\). We let \(\mathrm {FT}(\mu )\) denote the factorial tilting family generated by \( P\) with local dispersion function \(v\) on \(\Psi _{0}\). We may now complete the proof in the nonzero case by proceeding like in the proof of Proposition 2.1.
In the case where \(v(\mu )=0\) (the zero case), we cannot define the function \(\psi \) as above. Instead we take \(C(t)=t\mu _{0},\) such that \(\dot{C} (t)=\mu _{0}\) and \(\ddot{C}(t)=0\) for \(t\in \mathbb {R}\). For any \(\epsilon >0\), we may choose an \(n_{0}\) such that \(\left| v_{n}(\mu )\right| \le \epsilon \) for any \(n\ge n_{0}\) and \(\mu \in K\). For such \(n\) and \(\mu \), we hence obtain
which can be made arbitrarily large by choosing \(\epsilon \) small. We hence conclude that \(J_{n}=\psi _{n}(K)\rightarrow \mathbb {R}\) as \(n\rightarrow \infty \).
Now we let \(J\) be a compact interval such that \(0\in \mathrm {int}J\), implying that \(J\subseteq \,J_{n}\) for \(n\) large enough. For such \(n\) we hence obtain that \(\left| \ddot{C}_{n}(t)\right| =\left| v_{n}( \dot{C}_{n}(t))\right| \le \epsilon \) for all \(t\in J\), because then \(\dot{C}_{n}(t)\in K\). Since \(\mu _{0}=\dot{C}(t)=\dot{C}_{n}(0)\) we find, again by the mean value theorem, that for \(t\in J\),
This implies that \(\dot{C}_{n}(t)\rightarrow \dot{C}(t)\) uniformly in \(t\in J \). By similar arguments as above, we conclude that \(\mathrm {FT}_{n}(\mu _{0}) \) converges weakly to a probability measure \(P\) with FCGF \(C(t)=t\mu _{0}\), which implies the desired conclusion in the zero case, completing the proof.
Rights and permissions
About this article
Cite this article
Jørgensen, B., Kokonendji, C.C. Discrete dispersion models and their Tweedie asymptotics. AStA Adv Stat Anal 100, 43–78 (2016). https://doi.org/10.1007/s10182-015-0250-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10182-015-0250-z
Keywords
- Factorial cumulant generating function
- Factorial tilting family
- Infinite dilatability
- Multivariate discrete distribution
- Over-/underdispersion
- Poisson–Tweedie mixture