Chapter Eight

Sections 8.1 – 8.3

8.1 An estimator is a sample statistic used to estimate a population parameter. The value(s) assigned
to a population parameter based on the value of a sample statistic is called an estimate.

8.3 The sample mean x is the point estimator of the population mean μ. The margin of error is
E = zσ x .

8.5 The width of a confidence interval depends on E = zσ x = z σ ( )

n . When n increases, z σ( n )
decreases and the width of the confidence interval decreases. From Example 8−1 in the text, n =
25,

x = $145, and σ = $35. Then, σ x = σ n = 35 25 = $7 . The 90% confidence interval for μ is

x ± zσ x = 145 ± 1.65(7) = 145 ± 11.55 = $133.45 to $156.55 . The width of this interval is $156.55
– $133.45 = $23.10. If n = 100, but all other values remain the same,

σx =σ n = 35 100 = $3.50 , and the 90% confidence interval for μ is

x ± zσ x = 145 ± 1.65(3.50) = 145 ± 5.78 = $139.22 to $150.78 . The width of this interval is
$150.78 – $139.22 = $11.56. Thus, the 90% confidence interval for μ is narrower when n = 100
than when n = 25.

8.7 A confidence interval is an interval constructed around a point estimate. A confidence level
indicates how confident we are that the confidence interval contains the population parameter.

8.9 If we take all possible samples of a given size and construct a 99% confidence interval for μ from
each sample, we can expect about 99% of these confidence intervals will contain μ and 1% will
not.

129
130 Chapter Eight

8.11 n = 20, x = 24.5, σ = 3.1, and σ x = σ n = 3.1 20 = .69318107

a. x = 24.5
b. The 99% confidence interval for μ is
x ± zσ x = 24.5 ± 2.58(.69318107) = 24.5 ± 1.79 = 22.71 to 26.29

c. E = zσ x = 2.58(.69318107) = 1.79

8.13 n = 36, x = 74.8, σ = 15.3, and σ x = σ n = 15.3 36 = 2.55

a. The 90% confidence interval for μ is x ± zσ x = 74.8 ± 1.65(2.55) = 74.8 ± 4.21 = 70.59 to 79.01
b. The 95% confidence interval for μ is
x ± zσ x = 74.8 ± 1.96(2.55) = 74.8 ± 5.00 = 69.80 to 79.80
c. The 99% confidence interval for μ is
x ± zσ x = 74.8 ± 2.58(2.55) = 74.8 ± 6.58 = 68.22 to 81.38
d. Yes, the width of the confidence intervals increases as the confidence level increases. This
occurs because as the confidence level increases, the value of z increases.

8.15 x = 81.90 and σ = 6.30

a. n = 16, so σ x = σ n = 6.30 16 = 1.575

The 99% confidence interval for μ is
x ± zσ x = 81.90 ± 2.58(1.575) = 81.90 ± 4.06 = 77.84 to 85.96

b. n = 20, so σ x = σ n = 6.30 20 = 1.40872283

The 99% confidence interval for μ is
x ± zσ x = 81.90 ± 2.58(1.40872283) = 81.90 ± 3.63 = 78.27 to 85.53

c. n = 25, so σ x = σ n = 6.30 25 = 1.26

The 99% confidence interval for μ is
x ± zσ x = 81.90 ± 2.58(1.26) = 81.90 ± 3.25 = 78.65 to 85.15
d. Yes, the width of the confidence intervals decreases as the sample size increases. This occurs
because the standard deviation of the sample mean decreases as the sample size increases.

8.17 n = 35, x = (∑x)/n = 1342/35 = 38.34, σ = 2.65, and σ x = σ n = 2.65 35 = .44793176

a. x = 38.34
 Introductory Statistics, Mann, Seventh Edition - Student’s Solutions Manual 131

b. The 98% confidence interval for μ is

x ± zσ x = 38.34 ± 2.33(.44793176) = 38.34 ± 1.04 = 37.30 to 39.38

c. E = zσ x = 2.33(.44793176) = 1.04

8.19 a. E = 2.50, σ = 12.5, and z = 2.58 for 99% confidence level

z 2σ 2 (2.58) 2 (12.5) 2
n= = = 166.41 ≈ 167
E2 (2.50) 2

b. E = 3.20, σ = 12.5, and z = 2.05 for 96% confidence level

z 2σ 2 (2.05) 2 (12.5) 2
n= = = 64.13 ≈ 65
E2 (3.20) 2

8.21 a. E = 2.3, σ = 15.40, and z = 2.58 for 99% confidence level

z 2σ 2 (2.58) 2 (15.40) 2
n= = = 298.42 ≈ 299
E2 (2.3) 2

b. E = 4.1, σ = 23.45, and z = 1.96 for 95% confidence level

z 2σ 2 (1.96) 2 (23.45) 2
n= = = 125.67 ≈ 126
E2 (4.1) 2

c. E = 25.9, σ = 122.25, and z = 1.65 for 90% confidence level

z 2σ 2 (1.65) 2 (122.25) 2
n= 2
= = 60.65 ≈ 61
E (25.9) 2

8.23 n = 1500, x = $299,720, σ = $68,650, and σ x = σ n = 68,650 1500 = $1772.535378

The 99% confidence interval for μ is

x ± zσ x = 299,720 ± 2.58(1772.535378) = 299,720 ± 4573.14 = $295,146.86 to $304,293.14

8.25 n = 14, x = 53,550 labor-hours, σ = 7462 labor-hours, and

σx =σ n = 7462 14 = 1994.303387 labor-hours

a. The 98% confidence interval for μ is
x ± zσ x = 53,550 ± 2.33(1994.303387) = 53,550 ± 4646.73 = 48,903.27 to 58,196.73
labor-hours
132 Chapter Eight

b. The sample mean of 53,550 labor-hours is an estimate of μ based on a random sample.

Because of sampling error, this estimate might differ from the true mean, μ, so we make an
interval estimate to allow for this uncertainty and sampling error.

8.27 n = 25, x = 31.94 ounces, σ = .15 ounce, and σ x = σ n = .15 25 = .03 ounce

The 99% confidence interval for μ is

x ± zσ x = 31.94 ± 2.58(.03) = 31.94 ± .08 = 31.86 to 32.02 ounces
Since the upper limit, 32.02, is less than 32.15, and the lower limit, 31.86, is greater than 31.85,
the machine does not need an adjustment.

8.29 a. n = 120, x = $1575, σ = $215, and σ x = σ n = 215 120 = $19.62672498

The 97% confidence interval for μ is

x ± zσ x = 1575 ± 2.17(19.62672498) = 1575 ± 42.59 = $1532.41 to $1617.59
b. The width of the confidence interval obtained in part a may be reduced by:
1. Lowering the confidence level
2. Increasing the sample size
The second alternative is better because lowering the confidence level results in a less reliable
estimate for μ.

8.31 E = .04 ounce, σ = .20 ounce, and z = 2.58 for 99% confidence level

z 2σ 2 (2.58) 2 (.20) 2
n= = = 166.41 ≈ 167
E2 (.04) 2

8.33 E = .75 hour, σ = 2.5 hours, and z = 2.33 for 98% confidence level

z 2σ 2 (2.33) 2 (2.5) 2
n= = = 60.32 ≈ 61
E2 (.75) 2

8.35 To estimate μ, the mean age of cars at a 95% confidence level:

1. Take a random sample of 30 or more U.S. car owners.
2. Determine age of each car.
3. Find x , the mean of the sample.

4. Calculate σ x = σ n.
 Introductory Statistics, Mann, Seventh Edition - Student’s Solutions Manual 133

5. Calculate the 95% confidence interval for μ using the formula x ± 1.96σ x .

Section 8.4

8.37 The normal distribution has two parameters: μ and σ. Given the values of these parameters for a
normal distribution, we can find the area under the normal curve between any two points. The t
distribution has only one parameter: the degrees of freedom. The shape of the t distribution
curve is determined by the degrees of freedom.
8.39 The t distribution is used to construct a confidence interval for the population mean μ if the
following assumptions hold true:
Case I:
1. The population standard deviation σ is not known.
2. The sample size is small (i.e., n < 30).
3. The population from which the sample is drawn is (approximately) normally distributed.
Case II:
1. The population standard deviation σ is not known.
2. The sample size is large (i.e., n ≥ 30).

8.41 a. df = n – 1 = 21 – 1 = 20 and t = –1.325 b. df = n – 1 = 14 – 1 = 13 and t = 2.160

c. t = 3.281 d. t = –2.715

8.43 a. Area in the left tail = .10

b. df = n – 1 = 25 – 1 = 24, area in the right tail = .005
c. df = n – 1 = 9 – 1 = 8, area in the right tail = .10
d. Area in the left tail = .01

8.45 a. df = n – 1 = 22 – 1 = 21, α/2 = .5 – (.95/2) = .025, and t = 2.080

b. α/2 = .5 – (.90/2) = .05 and t = 1.671
c. df = n – 1 = 24 – 1 = 23, α/2 = .5 – (.99/2) = .005, and t = 2.807

8.47 n = 11, ∑x = 15.5, and ∑x2 = 534.49

x = (∑x)/n = 15.5/11 = 1.41

134 Chapter Eight

( x)
∑ x 2 − ∑n
2
(15.5)2
534.49 −
s= = 11 = 7.15995175
n −1 11 − 1

sx = s n = 7.15995175 11 = 2.15880668

a. x = 1.41
b. df = n – 1 = 11 – 1 = 10, α/2 = .5 – (.95/2) = .025, and t = 2.228
The 95% confidence interval for μ is
x ± ts x = 1.41 ± 2.228(2.15880668) = 1.41 ± 4.81 = −3.40 to 6.22

c. E = ts x = 2.228(2.15880668) = 4.81

8.49 n = 47, x = 25.5, s = 4.9, s x = s n = 4.9 47 = .71473846 , and df = n – 1 = 47 – 1 = 46

a. α/2 = .5 – (.95/2) = .025 and t = 2.013
The 95% confidence interval for μ is
x ± ts x = 25.5 ± 2.013(.71473846) = 25.5 ± 1.44 = 24.06 to 26.94
b. α/2 = .5 – (.99/2) = .005 and t = 2.687
The 99% confidence interval for μ is
x ± ts x = 25.5 ± 2.687(.71473846) = 25.5 ± 1.92 = 23.58 to 27.42
The width of the 99% confidence interval for μ is larger than that of the 95% confidence
interval. This is so because the value of t for a 99% confidence level is larger than that for a
95% confidence level.

c. s x = s n = 4.9 32 = .86620581
df = n – 1 = 32 – 1 = 31, α/2 = .5 – (.95/2) = .025 and t = 2.040
The 95% confidence interval for μ is
x ± ts x = 25.5 ± 2.040(.86620581) = 25.5 ± 1.77 = 23.73 to 27.27
The width of the 95% confidence interval for μ is larger with n = 32 than that of the 95%
confidence interval with n = 47. This is so because the value of the standard deviation of the
sample mean increases as sample size decreases.

8.51 In each of the following parts, since n = 400 is very large, we use the normal distribution to
approximate the t distribution, and construct the confidence interval using x ± zs x .

a. n = 400, x = 92.45, s = 12.20, and s x = s n = 12.20 400 = .61

 Introductory Statistics, Mann, Seventh Edition - Student’s Solutions Manual 135

The 98% confidence interval for μ is

x ± zs x = 92.45 ± 2.33(.61) = 92.45 ± 1.42 = 91.03 to 93.87

b. n = 400, x = 91.75, s = 14.50, and s x = s n = 14.50 400 = .725

The 98% confidence interval for μ is
x ± zs x = 91.75 ± 2.33(.725) = 91.75 ± 1.69 = 90.06 to 93.44

c. n = 400, x = 89.63, s = 13.40, and s x = s n = 13.40 400 = .67

The 98% confidence interval for μ is
x ± zs x = 89.63 ± 2.33(.67) = 89.63 ± 1.56 = 88.07 to 91.19
d. The confidence intervals of parts b and c cover μ but the confidence interval of part a does not.

8.53 n = 20, x = 41.2 bushels per acre, s = 3 bushels per acre, and s x = s n =3 20 = .67082039
bushel per acre
df = n – 1 = 20 – 1 = 19, α/2 = .5 – (.90/2) = .05, and t = 1.729
The 90% confidence interval for μ is
x ± ts x = 41.2 ± 1.729(.67082039) = 41.2 ± 1.16 = 40.04 to 42.36 bushels per acre

8.55 n = 32, x = .34 gram, s = .062 gram, and s x = s n = .062 32 = .01096016 gram
df = n – 1 = 32 – 1 = 31, α/2 = .5 – (.95/2) = .025, and t = 2.040
The 95% confidence interval for μ is x ± ts x = .34 ± 2.040(.01096016) = .34 ± .02 = .32 to .36 gram

8.57 n = 25, x = 22 minutes, s = 6 minutes, and s x = s n =6 25 = 1.2 minutes

df = n – 1 = 25 – 1 = 24, α/2 = .5 – (.99/2) = .005, and t = 2.797
The 99% confidence interval for μ is x ± ts x = 22 ± 2.797(1.2) = 22 ± 3.36 = 18.64 to 25.36
minutes

8.59 a. n = 40, x = 23 hours, s = 3.75 hours, and s x = s n = 3.75 40 = .59292706 hour

df = n – 1 = 40 – 1 = 39, α/2 = .5 – (.98/2) = .01, and t = 2.426
The 98% confidence interval for μ is
x ± ts x = 23 ± 2.426(.59292706) = 23 ± 1.44 = 21.56 to 24.44 hours
b. The width of the confidence interval obtained in part a can be reduced by:
1. Lowering the confidence level
136 Chapter Eight

2. Increasing the sample size

The second alternative is better because lowering the confidence level gives a less reliable
estimate for μ.

8.61 n = 9, ∑x = 72, and ∑x2 = 708

x = (∑x)/n = 72/9 = 8 hours

2 (∑ x ) 2
(72) 2
∑x − 708 −
s= n = 9 = 4.06201920 hours
n −1 9 −1

sx = s n = 4.06201920 9 = 1.35400640 hours

df = n – 1 = 9 – 1 = 8, α/2 = .5 – (.95/2) = .025, and t = 2.306
The 95% confidence interval for μ is
x ± ts x = 8 ± 2.306(1.35400640) = 8 ± 3.12 = 4.88 to 11.12 hours

8.63 n = 15, ∑x = 115, and ∑x2 = 891.88

x = (∑x)/n = 115/15 = 7.67 ounces

(∑ x )2 (115) 2
∑ x2 − n
891.88 −
15 = .85412166 ounce
s= =
n −1 15 − 1

sx = s n = .85412166 15 = .22053326 ounce

df = n – 1 = 15 – 1 = 14, α/2 = .5 – (.95/2) = .025, and t = 2.145
The 95% confidence interval for μ is
x ± ts x = 7.67 ± 2.145(.22053326) = 7.67 ± .47 = 7.20 to 8.14 ounces

8.65 Since n = 400 is very large, we use the normal distribution to approximate the t distribution, and
construct the confidence interval using x ± zs x .

n = 400, x = 6.18 years, s = 2.87 years, and s x = s n = 2.87 400 = .1435 year

a. x = 6.18 years

b. The 98% confidence interval for μ is

x ± zs x = 6.18 ± 2.33(.1435) = 6.18 ± .33 = 5.85 to 6.51 years
 Introductory Statistics, Mann, Seventh Edition - Student’s Solutions Manual 137

8.67 To estimate the mean waiting time, μ (assuming that waiting times are normally distributed):
1. Take a random sample of 45 customers at the bank.
2. Record the waiting time for each of the 45 customers.
3. Calculate the sample mean, the standard deviation, and s x .
4. Choose the confidence level and determine the t value for df = n − 1 = 45 − 1 = 44.
5. Construct the confidence interval for μ using x ± ts x .

Section 8.5

8.69 The sample proportion p̂ is the point estimator of p.

8.71 a. n = 80, p̂ = .85, qˆ = 1 − p̂ = 1 − .85 = .15, npˆ = (80)(.85) = 68, and nqˆ = (80)(.15) = 12

Since npˆ > 5 and nqˆ > 5, the sample size is large enough to use the normal distribution.

b. n = 110, p̂ = .98, q̂ = 1 − p̂ = 1 − .98 = .02, npˆ = (110)(.98) = 107.8, and

nqˆ = (110)(.02) = 2.2

Since nqˆ < 5, the sample size is not large enough to use the normal distribution.

c. n = 35, p̂ = .4, q̂ = 1 − p̂ = 1 − .4 = .6, npˆ = (35)(.4) = 14, and nqˆ = (35)(.6) = 21

Since npˆ > 5 and nqˆ > 5, the sample size is large enough to use the normal distribution.

d. n = 200, p̂ = .08, q̂ = 1 − p̂ = 1 − .08 = .92, npˆ = (200)(.08) = 16, and

nqˆ = (200)(.92) = 184

Since npˆ > 5 and nqˆ > 5, the sample size is large enough to use the normal distribution.

8.73 a. n = 1100, p̂ = .32, qˆ = 1 − p̂ = 1 − .32 = .68, and

s pˆ = pˆ qˆ / n = (.32)(.68) / 1100 = .01406479

The 90% confidence interval for p is

pˆ ± zs pˆ = .32 ± 1.65(.01406479) = .32 ± .023 = .297 to .343

b. n = 1100, p̂ = .36, qˆ = 1 − p̂ = 1 − .36 = .64, and

s pˆ = pˆ qˆ / n = (.36)(.64) / 1100 = .01447255

The 90% confidence interval for p is pˆ ± zs pˆ = .36 ± 1.65(.01447255) = .36 ± .024 = .336 to .384
138 Chapter Eight

c. n = 1100, p̂ = .30, qˆ = 1 − p̂ = 1 − .30 = .70, and

s pˆ = pˆ qˆ / n = (.30)(.70) / 1100 = .01381699

The 90% confidence interval for p is

pˆ ± zs pˆ = .30 ± 1.65(.01381699) = .30 ± .023 = .277 to .323

d. The confidence intervals of parts a and b cover p, but the confidence interval of part c does not.

8.75 n = 200, p̂ = .27, q̂ = 1 − p̂ = 1 − .27 = .73, and s pˆ = pˆ qˆ / n = (.27)(.73) / 200 = .03139267

a. The 99% confidence interval for p is

pˆ ± zs pˆ = .27 ± 2.58(.03139267) = .27 ± .081 = .189 to .351

b. The 97% confidence interval for p is

pˆ ± zs pˆ = .27 ± 2.17(.03139267) = .27 ± .068 = .202 to .338

c. The 90% confidence interval for p is

pˆ ± zs pˆ = .27 ± 1.65(.03139267) = .27 ± .052 = .218 to .322

d. Yes, the width of the confidence intervals decreases as the confidence level decreases. This
occurs because as the confidence level decreases, the value of z decreases.

8.77 p̂ = .31 and q̂ = 1 − p̂ = 1 − .31 = .69

a. n = 1200 and s pˆ = pˆ qˆ / n = (.31)(.69) / 1200 = .01335103

The 95% confidence interval for p is pˆ ± zs pˆ = .31 ± 1.96(.01335103) = .31 ± .026 = .284 to .336

b. n = 500 and s pˆ = pˆ qˆ / n = (.31)(.69) / 500 = .02068333

The 95% confidence interval for p is pˆ ± zs pˆ = .31 ± 1.96(.02068333) = .31 ± .041 = .269 to .351

c. n = 80 and s pˆ = pˆ qˆ / n = (.31)(.69) / 80 = .05170832

The 95% confidence interval for p is pˆ ± zs pˆ = .31 ± 1.96(.05170832) = .31 ± .101 = .209 to .411

d. Yes, the width of the confidence intervals increases as the sample size decreases. This occurs
because decreasing the sample size increases the standard deviation of the sample proportion.

8.79 a. E = .045, p̂ = .53, q̂ = 1 − p̂ = 1 − .53 = .47, and z = 2.33 for 98% confidence level
 Introductory Statistics, Mann, Seventh Edition - Student’s Solutions Manual 139

z 2 pˆ qˆ (2.33) 2 (.53)(.47)
n= 2
= = 667.82 ≈ 668
E (.045) 2

b. E = .045, p = q = .50 for the most conservative sample size, and z = 2.33 for 98% confidence
level

z 2 pq (2.33) 2 (.50)(.50)
n= = = 670.23 ≈ 671
E2 (.045) 2

8.81 a. E = .025, p̂ = .16, q̂ = 1 − p̂ = 1 − .16 = .84, and z = 2.58 for 99% confidence level

z 2 pˆ qˆ ( 2.58) 2 (.16)(.84)
n= = = 1431.39 ≈ 1432
E2 (.025) 2

b. E = .05, p̂ = .85, q̂ = 1 − p̂ = 1 − .85 = .15, and z = 1.96 for 95% confidence level

z 2 pˆ qˆ (1.96) 2 (.85)(.15)
n= = = 195.92 ≈ 196
E2 (.05) 2

c. E = .015, p̂ = .97, q̂ = 1 − p̂ = 1 − .97 = .03, and z = 1.65 for 90% confidence level

z 2 pˆ qˆ (1.65) 2 (.97)(.03)
n= = = 352.11 ≈ 353
E2 (.015) 2

8.83 n = 200, p̂ = 74/200 = .37, qˆ = 1 − p̂ = 1 − .37 = .63, and

s p̂ = pˆ qˆ / n = (.37)(.63) / 200 = .03413942

a. The 98% confidence interval for p is

pˆ ± zs pˆ = .37 ± 2.33(.03413942) = .37 ± .080 = .290 to .450

The corresponding interval for the population percentage is 29% to 45%.

b. The width of the confidence interval constructed in part a may be reduced by:
1. Lowering the confidence level
2. Increasing the sample size
The second alternative is better because lowering the confidence level results in a less reliable
estimate of p.

8.85 n = 240, p̂ = 96/240 = .40, qˆ = 1 − p̂ = 1 − .40 = .60, and

s p̂ = pˆ qˆ / n = (.40)(.60) / 240 = .03162278

a. pˆ = .40, so the point estimate for the population percentage is 40%

140 Chapter Eight

b. The 97% confidence interval for p is

pˆ ± zs pˆ = .40 ± 2.17(.03162278) = .40 ± .069 = .331 to .469

The corresponding interval for the population percentage is 33.1% to 46.9%.

8.87 a. n = 50, p̂ = 19/50 = .38, q̂ = 1 − p̂ = 1 − .38 = .62, and

s pˆ = pˆ qˆ / n = (.38)(.62) / 50 = .06864401

The 99% confidence interval for p is

pˆ ± zs pˆ = .38 ± 2.58(.06864401) = .38 ± .177 = .203 to .557

The corresponding interval for the population percentage is 20.3% to 55.7%.

b. The width of the confidence interval constructed in part a may be reduced by:
1. Lowering the confidence level
2. Increasing the sample size
The second alternative is better because lowering the confidence level gives a less reliable
estimate of p.

8.89 n = 855, p̂ = .147, q̂ = 1 − p̂ = 1 − .147 = .853, and

s p̂ = pˆ qˆ / n = (.147 )(.853) / 855 = .01211017

a. The 95% confidence interval for p is

pˆ ± zs pˆ = .147 ± 1.96(.01211017 ) = .147 ± .024 = .123 to .171

b. The sample proportion of .147 is an estimate of p based on a random sample. Because of

sampling error, this estimate might differ from the true proportion p, so we make an interval
estimate to allow for this uncertainty and sampling error.

8.91 n = 24, p̂ = 8/24 = .333, qˆ = 1 − p̂ = 1 − .333 = .667, and

s pˆ = pˆ qˆ / n = (.333)(.667 ) / 24 = .09620096

a. pˆ = .333
b. The 99% confidence interval for p is
pˆ ± zs pˆ = .333 ± 2.58(.09620096) = .333 ± .248 = .085 to .581

The corresponding interval for the population percentage is 8.5% to 58.1%.

 Introductory Statistics, Mann, Seventh Edition - Student’s Solutions Manual 141

8.93 E = .02, p̂ = .93, q̂ = 1 − p̂ = 1 − .93 = .07, and z = 2.58 for 99% confidence level

z 2 pˆ qˆ (2.58) 2 (.93)(.07)
n= = = 1083.33 ≈ 1084
E2 (.02) 2

8.95 E = .03, p = q = .50 for the most conservative sample size, and z = 2.58 for 99% confidence level

z 2 pq (2.58) 2 (.50)(.50)
n= = = 1849
E2 (.03) 2

8.97 To estimate the percentage of students who are satisfied with campus food services:
1. Take a random sample of 30 students who use campus food services.
2. Determine the number of students in this sample who are satisfied with the campus food
services.
3. Calculate pˆ and s pˆ .

4. Choose the confidence level and find the required value of z in the normal distribution table.
5. Construct the confidence interval for p using the formula pˆ ± zs pˆ .

6. Obtain the corresponding interval for the population percentage by multiplying the upper and
lower limits of the confidence interval for p by 100%.

Supplementary Exercises

8.99 n = 100, x = $2640, σ = $578, and σ x = σ n = 578 100 = $57.80

a. x = $2640
b. The 97% confidence interval for μ is
x ± zσ x = 2640 ± 2.17(57.80) = 2640 ± 125.43 = $2514.57 to $2765.43

8.101 n = 20, x = 3.99 inches, σ = .04 inch, and σ x = σ n = .04 20 = .00894427 inch

The 98% confidence interval for μ is

x ± zσ x = 3.99 ± 2.33(.00894427) = 3.99 ± .021 = 3.969 to 4.011 inches
Since the lower limit of the confidence interval is 3.969, which is less than 3.98, the machine
needs an adjustment.
142 Chapter Eight

8.103 n = 44, ∑x = 637.3, and ∑x2 = 11,038.55

x = (∑x)/n = 637.3/44 = 14.48 gallons

(∑ x )2 (637.3) 2
∑ x2 − n
11,038.55 −
44
s= = = 6.48403919 gallons
n −1 44 − 1

sx = s n = 6.48403919 44 = .97750569 gallon

df = n – 1 = 44 – 1 = 43, α/2 = .5 – (.95/2) = .025, and t = 2.017
The 95% confidence interval for μ is
x ± ts x = 14.48 ± 2.017(.97750569) = 14.48 ± 1.97 = 12.51 to 16.45 gallons

8.105 n = 18, x = 24 minutes, s = 4.5 minutes, and s x = s n = 4.5 18 = 1.06066017 minutes

df = n – 1 = 18 – 1 = 17, α/2 = .5 – (.95/2) = .025, and t = 2.110
The 95% confidence interval for μ is
x ± ts x = 24 ± 2.110(1.06066017) = 24 ± 2.24 = 21.76 to 26.24 minutes

8.107 Since n = 300 is very large, we use the normal distribution to approximate the t distribution, and
construct the confidence interval using x ± zs x .

n = 300, x = 4.5 hours, s = .75 hour, and s x = s n = .75 300 = .04330127 hour

The 98% confidence interval for μ is x ± zs x = 4.5 ± 2.33(.04330127) = 4.5 ± .10 = 4.40 to 4.60
hours

8.109 n = 10, ∑x = 1514, and ∑x2 = 229,646

x = (∑x)/n = 1514/10 = 151.40 calories

2 (∑ x ) 2
(1514) 2
∑x − 229,646 −
s= n = 10 = 6.88315173 calories
n −1 10 − 1

sx = s n = 6.88315173 10 = 2.17664369 calories

df = n – 1 = 10 – 1 = 9, α/2 = .5 – (.99/2) = .005, and t = 3.250
The 99% confidence interval for μ is
x ± ts x = 151.40 ± 3.250(2.17664369) = 151.40 ± 7.07 = 144.33 to 158.47 calories
 Introductory Statistics, Mann, Seventh Edition - Student’s Solutions Manual 143

8.111 n = 430, p̂ = .033, q̂ = 1 − p̂ = 1 − .033 = .967, and

s p̂ = pˆ qˆ / n = (.033)(.967 ) / 430 = .00861462

a. p̂ = .033
b. The 95% confidence interval for p is
pˆ ± zs pˆ = .033 ± 1.96(.00861462) = .033 ± .017 = .016 to .050

c. The player’s suspicion seems reasonable since .0526 falls outside the 95% confidence interval.

8.113 n = 16, p̂ = 5/16 = .313, qˆ = 1 − p̂ = 1 − .313 = .687, and

s pˆ = pˆ qˆ / n = (.313)(.687 ) / 16 = .11592859

The 97% confidence interval for p is pˆ ± zs pˆ = .313 ± 2.17(.11592859) = .313 ± .252 = .061 to .565

The corresponding interval for the population percentage is 6.1% to 56.5%.

8.115 E = $3500, σ = $31,500, and z = 1.65 for 90% confidence level

z 2σ 2 (1.65) 2 (31,500) 2
n= = = 220.52 ≈ 221
E2 (3500) 2

8.117 E = .05, p̂ = .63, q̂ = 1 − p̂ = 1 − .63 = .37, and z = 1.96 for 95% confidence level

z 2 pˆ qˆ (1.96) 2 (.63)(.37)
n= = = 358.19 ≈ 359
E2 (.05) 2

8.119 Let p1 = proportion of the population who “cut back on vacations or entertainment because of their
cost,” p2 = proportion of population who “failed to pay a bill on time,” and p3 = proportion of the
population who “have not gone to a doctor because of the cost.” Note that for n = 1004, n pˆ and

n qˆ exceed 5 for all of these proportions, so the sample is considered large.

p̂1 = .64, q̂1 = 1 − p̂1 = 1 − .64 = .36, and s pˆ1 = pˆ 1qˆ1 / n = (.64)(.36) / 1004 = .01514867

The 95% confidence interval for p1 is pˆ 1 ± zs pˆ1 = .64 ± 1.96(.01514867) = .64 ± .030 = .610 to .670

The corresponding interval for the population percentage is 61.0% to 67.0%.

p̂ 2 = .37, q̂2 = 1 − p̂ 2 = 1 − .37 = .63, and s pˆ 2 = pˆ 2 qˆ 2 / n = (.37 )(.63) / 1004 = .01523717

The 95% confidence interval for p2 is pˆ 2 ± zs pˆ 2 = .37 ± 1.96(.01523717) = .37 ± .030 = .340 to .400
144 Chapter Eight

The corresponding interval for the population percentage is 34.0% to 40.0%.

p̂3 = .25, q̂3 = 1 − p̂3 = 1 − .25 = .75, and s pˆ 3 = pˆ 3 qˆ3 / n = (.25)(.75) / 1004 = .01366576

The 95% confidence interval for p3 is pˆ 3 ± zs pˆ 3 = .25 ± 1.96(.01366576) = .25 ± .027 = .223 to .277

The corresponding interval for the population percentage is 22.3% to 27.7%.

(1) A confidence interval is a range of numbers (in this particular case proportions or percentages)
which gives an estimate for the true value of the population parameter. (2) A single percentage
that we assign as an estimate would almost always differ from the true value, hence a range with
the associated confidence level is more informative. (3) The 95% means that we are 95%
confident that this interval, calculated from this particular sample, actually contains the true value
of the population parameter. (4) We assume that the 1004 persons selected for the sample
constitute a random sample of adults.

8.121 E = 1.0 mile, s = 4.1 miles, and z = 1.96 for 95% confidence level; σ may be estimated by s

z2s2 (1.96) 2 (4.1) 2

n= = = 64.58 ≈ 65
E2 (1.0) 2

Thus, an additional 65 – 20 = 45 observations must be taken.

8.123 a. E = 100 cars, σ = 170 cars, and z = 2.58 for 99% confidence level

z 2σ 2 (2.58) 2 (170) 2
n= 2
= = 19.24 ≈ 20
E (100) 2

Note that since n < 30, we must assume that the number of cars passing each day is approximately
normally distributed, or we may take a larger (n ≥ 30) sample.

z 2σ 2 E n 100 20
b. Since n = , z= = = 1.64 which corresponds to a confidence level of
E 2 σ 272
approximately 90%.

z 2σ 2 zσ (2.58)(130)
c. Since n = 2
, E= = = 75 .
E n 20
Thus, they can be 99% confident that their point estimate is within 75 cars of the true average.

8.125 When the sample size is doubled, the margin of error is reduced by a factor of 2 2 . When the
sample size is quadrupled, the margin of error is reduced by a factor of 1/2. This relationship does
 Introductory Statistics, Mann, Seventh Edition - Student’s Solutions Manual 145

not hold true when calculating a confidence interval for the population mean with an unknown
population standard deviation for the following reasons:
1) While σ is constant, the sample standard deviation, s, is not. The sample standard deviation
will change with each sample.
2) If σ is unknown, the confidence interval is calculated with a t value. This value will change as
the sample size changes because the degrees of freedom will change.

8.127 Answers will vary. The following provide one possible example for each case.
a. n = 200, p̂ = .01, q̂ = 1 − p̂ = 1 − .01 = .99, and

s pˆ = pˆ qˆ / n = (.01)(.99) / 200 = .00703562

The 95% confidence interval for p is

pˆ ± zs pˆ = .01 ± 1.96(.00703562) = .01 ± .014 = −.004 to .024

b. n = 160, p̂ = .9875, qˆ = 1 − p̂ = 1 − .9875 = .0125, and

s p̂ = pˆ qˆ / n = (.9875)(.0125) / 160 = .00878342

The 95% confidence interval for p is

pˆ ± zs pˆ = .9875 ± 1.96(.00878342) = .9875 ± .0172 = .9703 to 1.0047

The value of the lower limit in the first interval is less than 0, and the value of the upper limit in
the second interval is greater than 1. These are not possible values for proportions.

Self – Review Test

1. a. Estimation means assigning values to a population parameter based on the value of a sample
statistic.
b. An estimator is the sample statistic used to estimate a population parameter.
c. The value of a sample statistic is called the point estimate of the corresponding population
parameter.

2. b 3. a 4. a 5. c 6. b
146 Chapter Eight

7. n = 36, x = $159,000, σ = $27,000, and σ x = σ n = 27,000 36 = $4500

a. x = $159,000
b. The 99% confidence interval for μ is
x ± zσ x = 159,000 ± 2.58(4500) = 159,000 ± 11,610 = $147,390 to $170,610

E = zσ x = 2.58(4500) = $11,610

8. n = 25, x = $410,425, s = $74,820, and s x = s n = 74,820 25 = $14,964

df = n – 1 = 25 – 1 = 24, α/2 = .5 – (.95/2) = .025, and t = 2.064
The 95% confidence interval for μ is
x ± ts x = 410,425 ± 2.064(14,964) = 410,425 ± 30,885.70 = $379,539.30 to $441,310.70

9. n = 450, p̂ = .55, qˆ = 1 − p̂ = 1 − .55 = .45, and s pˆ = pˆ qˆ / n = (.55)(.45) / 450 = .02345208

a. pˆ = .55

b. The 99% confidence interval for p is pˆ ± zs pˆ = .55 ± 2.58(.02345208) = .55 ± .061 = .489 to .611

10. E = 1.25 degrees, σ = 5.78 degrees, and z = 1.96 for 95% confidence level

z 2σ 2 (1.96) 2 (5.78) 2
n= = = 82.14 ≈ 83
E2 (1.25) 2

11. E = .05, p = q = .50 for the most conservative sample size, and z = 1.65 for 90% confidence level

z 2 pq (1.65) 2 (.50)(.50)
n= = = 272.25 ≈ 273.
E2 (.05) 2

12. E = .05, p̂ = .70, q̂ = 1 − p̂ = 1 − .70 = .30, and z = 1.65 for 90% confidence level

z 2 pˆ qˆ (1.65) 2 (.70)(.30)
n= = = 228.69 ≈ 229.
E2 (.05) 2

13. The width of the confidence interval can be reduced by:

1. Lowering the confidence level
2. Increasing the sample size
 Introductory Statistics, Mann, Seventh Edition - Student’s Solutions Manual 147

The second alternative is better because lowering the confidence level results in a less reliable
estimate for μ.

14. To estimate the mean number of hours that all students at your college work per week:
1. Take a random sample of 12 students from your college. (Note that if you want to estimate the
mean number of hours that all students at your college who hold jobs work per week, you would
limit your sample to students who hold jobs.)
2. Record the number of hours each of these students worked last week.
3. Calculate x , s and s x from these data.
4. After choosing the confidence level, find the value for the t distribution with 11 df and for an area
of α/2 in the right tail.
5. Construct the confidence interval for μ by using the formula x ± ts x .

You are assuming that the hours worked by all students at your college have a normal distribution.

15. To estimate the proportion of people who are happy with their current jobs:
1. Take a random sample of 35 workers.
2. Determine whether or not each worker is happy with his or her job.
3. Calculate pˆ , qˆ , and s p) .

4. Choose the confidence level and find the required value of z from the normal distribution table.
5. Construct the confidence interval for p by using the formula pˆ ± zs p) .
148 Chapter Eight