6.5Sampling Distributions from a Normal Population 215
6.5.1 Distribution of the Sample Mean
Since the sum of independent normal random variables is normally distributed, it follows
thatXis normal with mean
E[X]=
∑n
i= 1
E[Xi]
n
=μ
and variance
Var(X)=
1
n^2
∑n
i= 1
Var(Xi)=σ^2 /n
That is,X, the average of the sample, is normal with a mean equal to the population mean
but with a variance reduced by a factor of 1/n. It follows from this that
X−μ
σ/
√
n
is a standard normal random variable.
6.5.2 Joint Distribution ofXandS^2
In this section, we not only obtain the distribution of the sample varianceS^2 , but we also
discover a fundamental fact about normal samples — namely, thatXandS^2 are indepen-
dent with (n−1)S^2 /σ^2 having a chi-square distribution withn−1 degrees of freedom.
To start, for numbersx 1 ,...,xn, letyi=xi−μ,i=1,...,n. Then asy=x−μ,
it follows from the identity
∑n
i= 1
(yi−y)^2 =
∑n
i= 1
y^2 i−ny^2
that
∑n
i= 1
(xi−x)^2 =
∑n
i= 1
(xi−μ)^2 −n(x−μ)^2
Now, ifX 1 ,...,Xnis a sample from a normal population having meanμvarianceσ^2 ,
then we obtain from the preceding identity that
∑n
i= 1
(Xi−μ)^2
σ^2
=
∑n
i= 1
(Xi−X)^2
σ^2
+
n(X−μ)^2
σ^2