Natural exponential family

In probability and statistics, a natural exponential family (NEF) is a class of probability distributions that is a special case of an exponential family (EF).

Definition

edit

Univariate case

edit

The natural exponential families (NEF) are a subset of the exponential families. A NEF is an exponential family in which the natural parameter η and the natural statistic T(x) are both the identity. A distribution in an exponential family with parameter θ can be written with probability density function (PDF)   where   and   are known functions. A distribution in a natural exponential family with parameter θ can thus be written with PDF   [Note that slightly different notation is used by the originator of the NEF, Carl Morris.[1] Morris uses ω instead of η and ψ instead of A.]

General multivariate case

edit

Suppose that  , then a natural exponential family of order p has density or mass function of the form:   where in this case the parameter  

Moment and cumulant generating functions

edit

A member of a natural exponential family has moment generating function (MGF) of the form  

The cumulant generating function is by definition the logarithm of the MGF, so it is  

Examples

edit

The five most important univariate cases are:

These five examples – Poisson, binomial, negative binomial, normal, and gamma – are a special subset of NEF, called NEF with quadratic variance function (NEF-QVF) because the variance can be written as a quadratic function of the mean. NEF-QVF are discussed below.

Distributions such as the exponential, Bernoulli, and geometric distributions are special cases of the above five distributions. For example, the Bernoulli distribution is a binomial distribution with n = 1 trial, the exponential distribution is a gamma distribution with shape parameter α = 1 (or k = 1 ), and the geometric distribution is a special case of the negative binomial distribution.

Some exponential family distributions are not NEF. The lognormal and Beta distribution are in the exponential family, but not the natural exponential family. The gamma distribution with two parameters is an exponential family but not a NEF and the chi-squared distribution is a special case of the gamma distribution with fixed scale parameter, and thus is also an exponential family but not a NEF (note that only a gamma distribution with fixed shape parameter is a NEF).

The inverse Gaussian distribution is a NEF with a cubic variance function.

The parameterization of most of the above distributions has been written differently from the parameterization commonly used in textbooks and the above linked pages. For example, the above parameterization differs from the parameterization in the linked article in the Poisson case. The two parameterizations are related by  , where λ is the mean parameter, and so that the density may be written as   for  , so  

This alternative parameterization can greatly simplify calculations in mathematical statistics. For example, in Bayesian inference, a posterior probability distribution is calculated as the product of two distributions. Normally this calculation requires writing out the probability distribution functions (PDF) and integrating; with the above parameterization, however, that calculation can be avoided. Instead, relationships between distributions can be abstracted due to the properties of the NEF described below.

An example of the multivariate case is the multinomial distribution with known number of trials.

Properties

edit

The properties of the natural exponential family can be used to simplify calculations involving these distributions.

Univariate case

edit
  1. Natural exponential families (NEF) are closed under convolution.[2] Given independent identically distributed (iid)   with distribution from an NEF, then   is an NEF, although not necessarily the original NEF. This follows from the properties of the cumulant generating function.
  2. The variance function for random variables with an NEF distribution can be written in terms of the mean.[2]  
  3. The first two moments of a NEF distribution uniquely specify the distribution within that family of distributions.[2]  

Multivariate case

edit

In the multivariate case, the mean vector and covariance matrix are[citation needed]   where  is the gradient and   is the Hessian matrix.

Natural exponential families with quadratic variance functions (NEF-QVF)

edit

A special case of the natural exponential families are those with quadratic variance functions. Six NEFs have quadratic variance functions (QVF) in which the variance of the distribution can be written as a quadratic function of the mean. These are called NEF-QVF. The properties of these distributions were first described by Carl Morris. [3]

 

The six NEF-QVFs

edit

The six NEF-QVF are written here in increasing complexity of the relationship between variance and mean.

  1. The normal distribution with fixed variance   is NEF-QVF because the variance is constant. The variance can be written  , so variance is a degree 0 function of the mean.
  2. The Poisson distribution   is NEF-QVF because all Poisson distributions have variance equal to the mean  , so variance is a linear function of the mean.
  3. The Gamma distribution   is NEF-QVF because the mean of the Gamma distribution is   and the variance of the Gamma distribution is  , so the variance is a quadratic function of the mean.
  4. The binomial distribution   is NEF-QVF because the mean is   and the variance is   which can be written in terms of the mean as
     
  5. The negative binomial distribution   is NEF-QVF because the mean is   and the variance is  
  6. The (not very famous) distribution generated by the generalized[clarification needed] hyperbolic secant distribution (NEF-GHS) has[citation needed]   and  

Properties of NEF-QVF

edit

The properties of NEF-QVF can simplify calculations that use these distributions.

  1. Natural exponential families with quadratic variance functions (NEF-QVF) are closed under convolutions of a linear transformation.[4] That is, a convolution of a linear transformation of an NEF-QVF is also an NEF-QVF, although not necessarily the original one.

    Given independent identically distributed (iid)   with distribution from a NEF-QVF. A convolution of a linear transformation of an NEF-QVF is also an NEF-QVF.

    Let   be the convolution of a linear transformation of X. The mean of Y is  . The variance of Y can be written in terms of the variance function of the original NEF-QVF. If the original NEF-QVF had variance function   then the new NEF-QVF has variance function   where    

     
  2. Let   and   be independent NEF with the same parameter θ and let  . Then the conditional distribution of   given   has quadratic variance in   if and only if   and   are NEF-QVF. Examples of such conditional distributions are the normal, binomial, beta, hypergeometric and geometric distributions, which are not all NEF-QVF.[1]
  3. NEF-QVF have conjugate prior distributions on μ in the Pearson system of distributions (also called the Pearson distribution although the Pearson system of distributions is actually a family of distributions rather than a single distribution.) Examples of conjugate prior distributions of NEF-QVF distributions are the normal, gamma, reciprocal gamma, beta, F-, and t- distributions. Again, these conjugate priors are not all NEF-QVF.[1]
  4. If   has an NEF-QVF distribution and μ has a conjugate prior distribution then the marginal distributions are well-known distributions.[1] These properties together with the above notation can simplify calculations in mathematical statistics that would normally be done using complicated calculations and calculus.

See also

edit

References

edit
  1. ^ a b c d Morris C. (2006) "Natural exponential families", Encyclopedia of Statistical Sciences.
  2. ^ a b c Carl N. Morris. "Natural Exponential Families with Quadratic Variance Functions: Statistical Theory." Ann. Statist. 11 (2) 515 - 529, June, 1983. doi:10.1214/aos/1176346158
  3. ^ Morris, Carl (1982). "Natural Exponential Families with Quadratic Variance Functions". The Annals of Statistics. 10 (1): 65–80. doi:10.1214/aos/1176345690.
  4. ^ Morris, Carl; Lock, Kari F. (2009). "Unifying the Named Natural Exponential Families and Their Relatives". The American Statistician. 63 (3): 247–253. doi:10.1198/tast.2009.08145. S2CID 7095121.
  • Morris C. (1982) Natural exponential families with quadratic variance functions: statistical theory. Dept of mathematics, Institute of Statistics, University of Texas, Austin.