230 CHAPTER 7 POINT ESTIMATION OF PARAMETERSThe time to failure is exponentially distributed. Eight units are randomly selected and
tested, resulting in the following failure time (in hours): x 1 11.96, x 2 5.03, x 3 67.40, x 4
16.07, x 5 31.50, x 6 7.73, x 7 11.10, and x 8 22.38. Because , the moment
estimate of isEXAMPLE 7-4 Suppose that X 1 , X 2 ,, Xnis a random sample from a normal distribution with parameters
and ^2. For the normal distribution E(X) and E(X^2 ) ^2 ^2. EquatingE(X) to and
E(X^2 ) to givesSolving these equations gives the moment estimatorsNotice that the moment estimator of ^2 is not an unbiased estimator.EXAMPLE 7-5 Suppose that X 1 ,X 2 ,, Xnis a random sample from a gamma distribution with parametersr
and . For the gamma distribution and The moment esti-
mators are found by solvingThe resulting estimators areTo illustrate, consider the time to failure data introduced following Example 7-3. For this data,
and , so the moment estimates areWhen r1, the gamma reduces to the exponential distribution. Because slightly exceeds
unity, it is quite possible that either the gamma or the exponential distribution would provide
a reasonable model for the data.7-3.2 Method of Maximum LikelihoodOne of the best methods of obtaining a point estimator of a parameter is the method of maxi-
mum likelihood. This technique was developed in the 1920s by a famous British statistician,
Sir R. A. Fisher. As the name implies, the estimator will be the value of the parameter that
maximizes the likelihood function.rˆrˆ1 21.65 22(^11) 82 6639.40 1 21.65 22
1.30, ˆ
21.65(^11) 82 6639.40 1 21.65 22
0.0599
g
8
i 1 x
2
x21.65 i6639.40
rˆ
X^2
(^11) n (^2) a
n
i 1
X^2 iX^2 i
ˆ
X(^11) n (^2) a
n
i 1
X^2 iX^2
rX, r 1 r (^12) ^2
1
n^ a
n
i 1
X
2
i^
E 1 X 2 r E 1 X^22 r 1 r (^12) ^2.
p
ˆX, ˆ^2
ani 1Xi^2 a1
n^ ani 1X^2 ib2n ani 11 XiX 22nX, ^2 ^2
1
n^ ani 1X^2 i1
n^ gn
i 1 X
2
iXp (^1) x (^1) 21.650.0462.
x21.65
c 07 .qxd 5/15/02 10:18 M Page 230 RK UL 6 RK UL 6:Desktop Folder:TEMP WORK:MONTGOMERY:REVISES UPLO D CH114 FIN L:Quark Files: