• Bernoulli
  • Volume 13, Number 3 (2007), 623-640.

Local mixture models of exponential families

Karim Anaya-Izquierdo and Paul Marriott

Full-text: Open access


Exponential families are the workhorses of parametric modelling theory. One reason for their popularity is their associated inference theory, which is very clean, both from a theoretical and a computational point of view. One way in which this set of tools can be enriched in a natural and interpretable way is through mixing. This paper develops and applies the idea of local mixture modelling to exponential families. It shows that the highly interpretable and flexible models which result have enough structure to retain the attractive inferential properties of exponential families. In particular, results on identification, parameter orthogonality and log-concavity of the likelihood are proved.

Article information

Bernoulli, Volume 13, Number 3 (2007), 623-640.

First available in Project Euclid: 7 August 2007

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

affine geometry convex geometry differential geometry dispersion model exponential families mixture model statistical manifold


Anaya-Izquierdo, Karim; Marriott, Paul. Local mixture models of exponential families. Bernoulli 13 (2007), no. 3, 623--640. doi:10.3150/07-BEJ6170.

Export citation


  • Amari, S.-I. (1985). Differential-Geometrical Methods in Statistics. New York: Springer.
  • Anaya-Izquierdo, K. (2006). Statistical and geometric analysis of local mixture models and a proposal of some new tests of fit for censored data. Ph.D. thesis, Universidad Nacional Autónoma de México.
  • Anaya-Izquierdo, K. and Marriott, P. (2007). Local mixtures of negative exponential distribution. AISM 59 111–134.
  • Barvinok, A. (2002). A Course in Convexity. Providence, RI: Amer. Math. Soc.
  • Cox, D.R. (1983). Some remarks on overdispersion. Biometrika 70 269–274.
  • Critchley, F. and Marriott, P. (2004). Data-informed influence analysis. Biometrika 91 125–140.
  • Crowder, M.J. (1978). Beta-binomial ANOVA for proportions. Appl. Statist. 27 34–37.
  • Firth, D. (1987). On the efficiency of quasi-likelihood estimation. Biometrika 74 233–245.
  • Jørgensen, B. (1997). The Theory of Dispersion Models. London: Chapman and Hall.
  • Letac, G. and Mora, M. (1990). Natural real exponential families with cubic variance functions. Ann. Statist. 18 1–37.
  • Marriott, P. (2002). On the local geometry of mixture models. Biometrika 89 77–93.
  • Marriott, P. (2003). On the geometry of measurement error models. Biometrika 90 567–576.
  • McCullagh, P. (1983). Quasi-likelihood functions. Ann. Statist. 11 59–67.
  • Morris, C.N. (1982). Natural exponential families with quadratic variance functions. Ann. Statist. 10 65–80.
  • Morris, C.N. (1983). Natural exponential families with quadratic variance functions: Statistical theory. Ann. Statist. 11 515–529.
  • Phelps, R. (1966). Lectures on Choquet's theorem. New York: D. van Nostrand.
  • Shaked, M. (1980). On mixtures from exponential families. J. Roy. Statist. Soc. Ser. B 42 192–198.
  • Teuscher, F. and Guiard, V. (1995). Sharp inequalities between skewness and kurtosis for unimodal distributions. Statist. Probab. Lett. 22 257–260.
  • Wong, R. (2001). Asymptotic Approximations of Integrals. Philadelphia: SIAM.