8.3Tests Concerning the Mean of a Normal Population 299
it follows, since is an increasing function, that
(
μ 0 −μ 1
σ/
√
n
−zα/2
)
≤ (−zα/2)=P{Z≤−zα/2}=P{Z≥zα/2}=α/2
Hence, we can take
(
μ 0 −μ 1
σ/
√
n
−zα/2
)
≈ 0
and so from Equation 8.3.5
β≈
(
μ 0 −μ 1
σ/
√
n
+zα/2
)
(8.3.6)
or, since
β=P{Z>zβ}=P{Z<−zβ}= (−zβ)
we obtain from Equation 8.3.6 that
−zβ≈(μ 0 −μ 1 )
√
n
σ
+zα/2
or
n≈
(zα/2+zβ)^2 σ^2
(μ 1 −μ 0 )^2
(8.3.7)
In fact, the same approximation would result whenμ 1 <μ 0 (the details are left as an
exercise) and so Equation 8.3.7 is in all cases a reasonable approximation to the sample
size necessary to ensure that the type II error at the valueμ=μ 1 is approximately equal
toβ.
EXAMPLE 8.3d For the problem of Example 8.3a, how many signals need be sent so that
the .05 level test ofH 0 :μ=8 has at least a 75 percent probability of rejection when
μ=9.2?
SOLUTION Sincez.025=1.96,z.25=.67, the approximation 8.3.7 yields
n≈
(1.96+.67)^2
(1.2)^2
4 =19.21
Hence a sample of size 20 is needed. From Equation 8.3.4, we see that withn= 20
β(9.2)=
(
−
1.2
√
20
2
+1.96
)
−
(
−
1.2
√
20
2
−1.96
)
= (−.723)− (−4.643)