请输入您要查询的字词:

 

单词 SufficientStatistic
释义

sufficient statistic


Let {fθ} be a statistical model with parameterθ. Let 𝑿=(X1,,Xn) be a random vectorof random variablesMathworldPlanetmath representing n observations. A statisticMathworldMathworldPlanetmath T=T(𝑿) of 𝑿 for the parameter θ is called asufficient statistic, or a sufficient estimator, ifthe conditional probability distribution of 𝑿 givenT(𝑿)=t is not a function of θ (equivalently,does not depend on θ).

In other words, all the information about the unknown parameterθ is captured in the sufficient statistic T. If, say, weare interested in finding out the percentage of defective lightbulbs in a shipment of new ones, it is enough, or sufficient,to count the number of defective ones (sum of the Xi’s), ratherthan worrying about which individual light bulbs are the defectiveones (the vector (X1,,Xn)). By taking the sum, a certain“reduction” of data has been achieved.

Examples

  1. 1.

    Let X1,,Xn be n independentPlanetmathPlanetmath observations from auniform distributionMathworldPlanetmath on integers 1,,θ. LetT=max{X1,,Xn} be a statistic for θ.Then the conditional probability distribution of𝑿=(X1,,Xn) given T=t is

    P(𝑿t)=P(X1=x1,,Xn=xn,max{Xn}=t)P(max{Xn}=t).

    The numerator is 0 ifmax{xn}t. So in this case,P(𝑿t)=0 and is not a function of θ.Otherwise, the numerator is θ-n and P(𝑿t) becomes

    θ-nP(max{Xn}=t)=(θnP(X(1)X(n)=t))-1,

    whereX(i)’s are the rearrangements of the Xi’s in anon-decreasing order from i=1 to n. For the denominator, we first note that

    P(X(1)X(n)=t)=P(X(1)X(n)t)-P(X(1)X(n)<t)
    =P(X(1)X(n)t)-P(X(1)X(n)t-1).

    From the above equation, we find that there are tn-(t-1)n ways to form non-decreasing finite sequencesPlanetmathPlanetmath of n positive integers such that the maximum of the sequence ist. So

    (θnP(X(1)X(n)=t))-1=(θn(tn-(t-1)n)θ-n)-1=(tn-(t-1)n)-1

    again is not a function of θ. Therefore, T=max{Xi} is asufficient statistic for θ.Here, we see that a reduction of data has been achieved by takingonly the largest member of set of observations, not the entire set.

  2. 2.

    If we set T(X1,,Xn)=(X1,,Xn), then we seethat T is trivially a sufficient statistic for anyparameter θ. The conditional probability distribution of(X1,,Xn) given T is 1. Even though this is a sufficientstatistic by definition (of course, the individual observationsprovide as much information there is to know about θ aspossible), and there is no loss of data in T (which is simply alist of all observations), there is really no reduction of data tospeak of here.

  3. 3.

    The sample mean

    X¯=X1++Xnn

    of n independent observations from a normal distributionMathworldPlanetmathN(μ,σ2) (both μ and σ2 unknown) is asufficient statistic for μ. This is the result of thefactorization criterion. Similarly, one sees that any partitionMathworldPlanetmathPlanetmath ofthe sum of n observations Xi into m subtotals is a sufficientstatistic for μ. For instance,

    T(X1,,Xn)=(i=1jXi,i=j+1kXi,i=k+1nXi)

    is a sufficient statistic for μ.

  4. 4.

    Again, assume there are n independent observations Xi froma normal distribution N(μ,σ2) with unknown mean andvarianceMathworldPlanetmath. The sample variance

    1n-1i=1n(Xi-X¯)2

    is not asufficient statistic for σ2. However, if μ is a knownconstant, then

    1n-1i=1n(Xi-μ)2

    is a sufficient statisticfor σ2.

A sufficient statistic for a parameter θ is calleda minimal sufficient statistic if it can be expressed as afunction of any sufficient statistic for θ.

Example. In example 3 above, both the sample meanX¯ and the finite sum S=X1++Xn are minimalsufficient statistics for the mean μ. Since, by thefactorization criterion, any sufficient statistic T for μ is avector whose coordinates form a partition of the finite sum, takingthe sum of these coordinates is just the finite sum S. So, wehave just expressed S as a function of T. Therefore, S isminimalPlanetmathPlanetmath. Similarly, X¯ is minimal.

Two sufficient statistics T1,T2 for a parameter θ aresaid to be equivalentMathworldPlanetmathPlanetmathPlanetmathPlanetmath provided that there is a bijectionMathworldPlanetmath g suchthat gT1=T2. X¯ and S from the aboveexample are two equivalent sufficient statistics. Two minimal sufficient statistics for the same parameter are equivalent.

Titlesufficient statistic
Canonical nameSufficientStatistic
Date of creation2013-03-22 15:02:42
Last modified on2013-03-22 15:02:42
OwnerCWoo (3771)
Last modified byCWoo (3771)
Numerical id11
AuthorCWoo (3771)
Entry typeDefinition
Classificationmsc 62B05
Synonymsufficient estimator
Synonymminimally sufficient statistic
Synonymminimal sufficient
Synonymminimally sufficient
Definesminimal sufficient statistic
Definesequivalent statistic
随便看

 

数学辞典收录了18232条数学词条,基本涵盖了常用数学知识及数学英语单词词组的翻译及用法,是数学学习的有利工具。

 

Copyright © 2000-2023 Newdu.com.com All Rights Reserved
更新时间:2025/5/4 12:52:36