In statistics a uniformly minimum-variance unbiased estimator or minimum-variance unbiased estimator (often abbreviated as UMVU or MVUE) is an unbiased estimator that has lower variance than any other unbiased estimator for all possible values of the parameter. Consider estimation of g(theta) based on data X_1, X_2, ldots, X_n i.i.d. from some family of densities p_theta, theta in Omega, where Omega is the parameter space. An unbiased estimator delta(X_1, X_2, ldots, X_n) of g(theta) is UMVU if forall theta in Omega,

mathrm{var}(delta(X_1, X_2, ldots, X_n)) leq mathrm{var}(tilde{delta}(X_1, X_2, ldots, X_n))

for any other unbiased estimator tilde{delta}.

If an unbiased estimator of g(theta) exists, then one can prove there is an essentially unique MVUE estimator. Using the Rao-Blackwell theorem one can also prove that determining the MVUE estimator is simply a matter of finding a complete sufficient statistic for the family p_theta, theta in Omega and conditioning any unbiased estimator on it. Put formally, suppose delta(X_1, X_2, ldots, X_n) is unbiased for g(theta), and that T is a complete sufficient statistic for the family of densities. Then

eta(X_1, X_2, ldots, X_n) = mathrm{E}(delta(X_1, X_2, ldots, X_n)|T),

is the MVUE estimator for g(theta).

Estimator selection

An efficient estimator need not exist, but if it does, it's the MVUE. Since the mean squared error (MSE) of an estimator delta is

MSE(delta) = mathrm{var}(delta) + mathrm{bias}(delta)^{2}

the MVUE minimizes MSE among unbiased estimators. In some cases biased estimators have lower MSE; see estimator bias.


Consider the data to be a single observation from an absolutely continuous distribution on mathbb{R} with density

p_theta(x) = frac{ theta e^{-x} }{(1 + e^{-x})^{theta + 1} }

and we wish to find the UMVU estimator of

g(theta) = frac{1}{theta^{2}}

First we recognize that the density can be written as

frac{ e^{-x} } { 1 + e^{-x} } exp(-theta log(1 + e^{-x}) + log(theta))

Which is an exponential family with sufficient statistic T = mathrm{log}(1 + e^{-x}). In fact this is a full rank exponential family, and therefore T is complete sufficient. See exponential family for a derivation which shows

mathrm{E}(T) = frac{1}{theta}, mathrm{var}(T) = frac{1}{theta^{2}}


mathrm{E}(T^2) = frac{2}{theta^{2}}

Clearly delta(X) = frac{T^2}{2} is unbiased, thus the UMVU estimator is

eta(X) = mathrm{E}(delta(X) | T) = mathrm{E}(frac{T^2}{2} | T) = frac{T^{2}}{2} = frac{log(1 + e^{-X})^{2}}{2}

This example illustrates that an unbiased function of the complete sufficient statistic will be UMVU.

See also



Search another word or see minimumon Dictionary | Thesaurus |Spanish
Copyright © 2015, LLC. All rights reserved.
  • Please Login or Sign Up to use the Recent Searches feature