Fundamentals of Probability and Statistics for Engineers

(John Hannent) #1

variance of any unbiased estimator and it expresses a fundamental limitation
on the accuracy with which a parameter can be estimated. We also note that
this lower bound is, in general, a function of , the true parameter value.
Several remarks in connection with the Crame ́r–Rao lower bound (CRLB)
are now in order.


Remark 1: the expectation in Equation (9.26) is equivalent to
,or

This alternate expression offers computational advantages in some cases.
Remark 2: the result given by Equation (9.26) can be extended easily to
multiple parameter cases. Let 1 , 2 ,..., and be the unknown
parameters in which are to be estimated on the basis of a
sample of size n. In vector notation, we can write

with corresponding vector unbiased estimator

F ollowing similar steps in the derivation of Equation (9.26), we can show that
the Crame ́r–Rao inequality for multiple parameters is of the form

where^1 is the inverse of matrix for which the elements are

Equation (9.39) implies that

where is the jjth element of^1.
Remark 3: the CRLB can be transformed easily under a transformation of
the parameter. Suppose that, instead of , parameter is of interest,

Parameter Estimation 269




.
Efq^2 lnfX;)/q^2 g


^2 ^nE
q^2 lnf…X;†
q^2

 1

: … 9 : 36 †

.


  mmn)
fx; 1 ,...,m),

qTˆ‰ 1  2  mŠ; … 9 : 37 †

Q^Tˆ‰^ 1 ^ 2  ^mŠ: … 9 : 38 †

covfQ^g

^1

n

; … 9 : 39 †

 

ijˆE

qlnf…X;q†
qi

qlnf…X;q†
qj



; i;jˆ 1 ; 2 ;...;m: … 9 : 40 †

varf^jg

…^1 †jj
n



1

njj

; jˆ 1 ; 2 ;...;m; … 9 : 41 †

^1 )jj 

 ˆg)

.

Free download pdf