Because learning changes everything.

Chapter 9

Estimation and Confidence Intervals

© McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC.
 Learning Objectives
LO9-1 Compute and interpret a point estimate of a
population mean.
LO9-2 Compute and interpret a confidence interval for a
population mean.
LO9-3 Compute and interpret a confidence interval for a
population proportion.
LO9-4 Adjust a confidence interval for finite populations.
LO9-5 Calculate the required sample size to estimate a
population proportion or population mean.

© McGraw Hill 2
 Introduction
• We transition from population parameters to sample
statistics.
• Use sample information to estimate the values of
unknown population parameters.
• We begin by studying point estimates.
• Given an adequate sample size, the sample mean is a
normally distributed random variable.
• Account for sampling error by using the standard error
of the sampling distribution to compute an interval
estimate of a population parameter.

© McGraw Hill 3
 Point Estimate for a Population Mean
A point estimate is a single value (statistic) used to estimate
a population value (parameter).
Point Estimate The statistic, computed from sample
information, that estimates a population parameter.
Example: Suppose the Bureau of Tourism for Barbados
wants an estimate of the mean amount spent by tourists
visiting that country.
• They randomly select 500 tourists as they depart and ask
these tourists about their spending while there.
• The mean amount spent by the sample of 500 tourists
serves as an estimate of the unknown population
parameter.
© McGraw Hill 4
 Confidence Intervals for a Population Mean 1

Confidence Interval A range of values constructed from

sample data so that the population parameter is likely to
occur within that range at a specified probability. The
specified probability is called the level of confidence.
• Estimate  with x in two situations.
1. The population standard deviation ( ) is known

2. The population standard deviation ( ) is unknown

© McGraw Hill 5
 Confidence Intervals for a Population Mean 2

Central limit theorem: The sampling distribution of the sample mean is

normally distributed.
• Mean:  .

• Standard deviation (standard error): .
n
Allows us to make confidence interval statements using z-statistics.
• 95% of all confidence intervals will contain the population mean. The
z-statistic is 1.96.
• 90% of all confidence intervals will contain the population mean. The
z-statistic is 1.65.
Confidence level: The percentage of similarly constructed intervals that
would include the parameter.

© McGraw Hill 6
 Confidence Intervals for a Population Mean 3

• Suppose you want the z-value for a 95% confidence interval.

• Divide the confidence level in half: .9500/2 = .4750.
• Find the value .4750 in the body of the table.

• The probability of finding a value between 0 and 1.96 is .4750.

• So the probability of finding a value between +/− 1.96 is .9500.
Access the text alternative for slide images.

© McGraw Hill 7
 Confidence Intervals for a Population Mean 4

Access the text alternative for slide images.

© McGraw Hill 8
 Confidence Intervals for a Population Mean 5

The width of the interval is determined by two factors.

• The level of confidence.

• The size of the standard error .
n
The standard error is affected by two values.
• The standard deviation,  .
• The number of observations in the sample, n.

Confidence interval for with  known : x  z
n

• 95%: x  1.96
n

• 90%: x  1.65
n

© McGraw Hill 9
 Confidence Intervals for a Population Mean 6

• Example: The American Management Association is

studying the income of store managers in the retail
industry.
• A random sample of 49 managers reveals a sample mean
of $45,420.
• The standard deviation of the population is $2,050.
• What is a reasonable range of values for the population
mean?
• How do we interpret these results?

© McGraw Hill 10
 Confidence Intervals for a Population Mean 7

• Example continued.
• The sample mean x = $63, 400 and  = $2, 050.
 $2, 050
• xz = $63, 400  1.96 = $63, 400  $574.
n 49
• $574 is called the margin of error.
• The interval is $62,826 to $63,974.
• We expect 95% of all confidence intervals computed from
random samples selected from the population will contain the
population mean.

© McGraw Hill 11
 Confidence Intervals for a Population Mean 8

• Example continued.

Access the text alternative for slide images.

© McGraw Hill 12
 Confidence Intervals for a Population Mean 9

• In most cases, the population standard deviation is not known.

• Use the sample standard deviation, s, to estimate the population
standard deviation,  .
• We cannot use the z-distribution.
x −
• Use the t-distribution: t = .
s/ n

• There is a difference between the

z-distribution and the t-
distribution, especially when the
sample sizes are small.

© McGraw Hill 13
 Confidence Intervals for a Population Mean 10

The t-distribution is based on the assumption that the

population of interest is normal.
There is a family of t distributions, depending on the degrees
of freedom (df) tied to sample size.
A continuous distribution, mound-shaped and symmetrical.

• Mean of 0.
• Standard deviation
differs by df.

© McGraw Hill 14
 Confidence Intervals for a Population Mean 11

• It is flatter (more spread out) than the standard normal

distribution, less peaked in the middle.
• As the df increases, the t-distribution approaches the z-
distribution.

© McGraw Hill 15
 Confidence Intervals for a Population Mean 12

• The t-distribution has greater spread than the z-

distribution.
• The value of t for a given confidence level has to be
larger than the value of z.

© McGraw Hill 16
 Confidence Intervals for a Population Mean 13

Access the text alternative for slide images.

© McGraw Hill 17
 Confidence Intervals for a Population Mean 14

• Confidence interval for with  unknown: x  t s .

n
• df = n − 1.

Access the text alternative for slide images.

© McGraw Hill 18
 Confidence Intervals for a Population Mean 15

• Example: A tire manufacturer wishes to investigate the

tread life of its tires.
• A sample of 10 tires driven 50,000 miles revealed a
sample mean of 0.32 inch of tread remaining with a
standard deviation of 0.09 inch.
• Construct a 95% confidence interval for the population
mean.
• Would it be reasonable for the manufacturer to conclude
that after 50,000 miles the population mean amount of
tread remaining is 0.30 inch?

© McGraw Hill 19
 Confidence Intervals for a Population Mean 16

• Example continued.
• x = 0.32, s = 0.09, n = 10.
• df = n − 1 = 10 − 1 = 9, the t-value is t = 2.262.

Access the text alternative for slide images.

© McGraw Hill 20
 Confidence Intervals for a Population Mean 17

• Example continued.
s 0.09
• x t = 0.32  2.262 = 0.32  0.064.
n 10
• 0.064 is the margin of error.
• The interval is 0.256 to 0.384.
• If we repeated this study, about 95% of the intervals would
include the population mean.
• Because 0.30 is in the interval, it is possible the population
mean is 0.30.
• But there are lots of other values!

© McGraw Hill 21
 A Confidence Intervals for a Population
Proportion 1

Proportion The fraction, ratio, or percent indicating the part of the

sample or the population having a particular trait of interest.
x
The sample proportion: p = .
n
The population proportion:  .
p estimates the true population proportion .
Binomial conditions.
• Two mutually exclusive outcomes.
• n independent trials.
• Same probability of success,  , in each trial.

© McGraw Hill 22
 A Confidence Intervals for a Population
Proportion 2

When n  5 and n(1 −  )  5, apply the central limit theorem.

• Distribution of the sample proportion is normal.
• Use z-values to compute the margin of error for a confidence
interval.

p(1 − p)
pz .
n
p(1 − p)
Standard error of the sample proportion: .
n
p(1 − p)
Margin of error: z .
n

© McGraw Hill 23
 A Confidence Intervals for a Population
Proportion 3

• Example: The union representing the Bottle Blowers of

America (BBA) is considering a proposal to merge with
the Teamsters Union.
• At least three-fourths of the BBA membership must
approve any merger.
• A random sample of 2,000 current members reveals
1,600 plan to vote for the merger proposal.
• What is the estimate of the population proportion?
• Can you conclude that the necessary proportion of BBA
members favor the merger? Why?

© McGraw Hill 24
 A Confidence Intervals for a Population
Proportion 4

• Example continued.
x 1, 600
• p= = = .80.
n 2, 000
• z =1.96.

p(1 − p) .80(1 − .80)

• pz = .80  1.96 = 0.80  0.018.
n 2, 000
• We estimate that the population proportion is between 0.782 to .818
with 95% confidence.
• Because the interval includes values larger than 0.75, we conclude
that the merger proposal will likely pass.

© McGraw Hill 25
 Finite Population Adjustment 1

The populations we have sampled so far have been very

large or infinite.
What if the sampled population is not very large?
If the sample is a substantial percentage of the population,
the estimate of the population parameter is more precise.
Adjust the standard error by the finite-population.
N −n
correction factor: .
N −1
• N is the population size.
• n is the sample size.

© McGraw Hill 26
 Finite Population Adjustment 2

• This will make your estimate more precise by reducing the

standard error.
Fraction of Correction
Sample Size Population Factor
10 .010 .9955
25 .025 .9879
50 .050 .9752
100 .100 .9492
200 .200 .8949
500 .500 .7075

© McGraw Hill 27
 Finite Population Adjustment 3

• Example: There are 250 families residing in Scandia,

Pennsylvania.
• A random sample of 40 of these families revealed the
mean annual church contribution was $450 and the
standard deviation was $75.
• What is the population mean? What is the best
estimate of the population mean?
• Develop a 90% confidence interval for the population
mean.
• Using the confidence interval, explain why the
population mean could be $445. Could the population
mean be $425? Why?

© McGraw Hill 28
 Finite Population Adjustment 4

• Example continued.
• x = $450, s = $75, n = 40, N = 250.
• df = 39, the t-value is t = 1.685.
• Use $450 as the estimate of the population mean.

$75 250 − 40
• $450  1.685 = $450  $18.35.
40 250 − 1
• The endpoints of the confidence interval are $431.65 and $468.35.
• It is likely the population mean is $445 but not $425.

© McGraw Hill 29
 Choosing an Appropriate Sample Size 1

The sample size is important to the standard error of a confidence

interval.
Sample size is not a variable but a decision based on:
• Margin of error.
• Level of confidence.
• Variation or dispersion.

The margin of error is designated as E.

• Amount added/subtracted from the estimate.
• Amount of error we are willing to tolerate.
• Small margin of error requires a large sample size.
• Larger margin of error gives a wider confidence interval.

© McGraw Hill 30
 Choosing an Appropriate Sample Size 2


For a mean, E = z .
n
 z 
• Solve for n to get n =  .
 E 
• Usually not a whole number, round up.
 (1 −  )
For a proportion, E = z .
n
2
z
• n =  (1 −  )   .
E
• If no reliable estimate of  is available, use  = .50.
•  (1 −  ) is maximized at  = .50.
• This will overstate the samples size.

© McGraw Hill 31
 Choosing an Appropriate Sample Size 3

• Example: A student in public administration wants to

estimate the mean monthly earnings of city council
members in large cities.
• She can tolerate a margin of error of $100 in estimating
the mean.
• She would also prefer to report the interval estimate with
a 95% level of confidence.
• The student found a report by the Department of Labor
that reported a standard deviation of $1,000.
• What is the required sample size?

© McGraw Hill 32
 Choosing an Appropriate Sample Size 4

• Example continued.

• E = $100,  = $1000, z = 1.96.

 z   (1.96)($1, 000) 
2 2

• n= =
   = (19.6) 2
= 384.16.
 E   $100 

• The computed value of 384.16 is rounded up to 385.

• A sample size of 385 is required to meet the specifications.

© McGraw Hill 33
 Choosing an Appropriate Sample Size 5

• Example: The student in the previous example also

wants to estimate the proportion of cities that have
private refuse collectors.
• The student wants to estimate the population proportion
with a margin of error of .10.
• Use a level of confidence of 90%.
• No estimate for the population proportion.
• What is the required sample size?

© McGraw Hill 34
 Choosing an Appropriate Sample Size 6

• Example continued.

• E = 0.10, z = 1.645 and assume  = .50.

2 2
z  1.645 
• n =  (1 −  )   = .50(1 − .50)   = 67.25.
E  .10 

• The student needs a random sample of 68 cities.

© McGraw Hill 35
 Chapter 9 Practice Problems

© McGraw Hill 36
 Question 5 LO9-1, 2

A research firm surveyed 49 randomly selected Americans

to determine the mean amount spent on coffee during 1
week. The sample mean was $20 per week. The
population distribution is normal with a standard deviation
of $5.

a. What is the point estimate of the population mean?

Explain what it indicates.
b. Using the 95% level of confidence, determine the
confidence interval for μ. Explain what it indicates.

© McGraw Hill 37
 Question 13 LO9-2

The owner of Britten’s Egg Farm wants to estimate the mean number
of eggs produced per chicken. A sample of 20 chickens shows they
produced an average of 20 eggs per month with a standard deviation
of 2 eggs per month.

a. What is the value of the population mean? What is the best

estimate of this value?
b. Explain why we need to use the t distribution. What assumption do
you need to make?
c. For a 95% confidence interval, what is the value of t?
d. What is the margin of error?
e. Develop the 95% confidence interval for the population mean.
f. Would it be reasonable to conclude that the population mean is 21
eggs? What about 25 eggs?

© McGraw Hill 38
 Question 17 LO9-3

• The owner of the West End Kwick fill Gas Station wishes
to determine the proportion of customers who pay at the
pump using a credit card or debit card. He surveys 100
customers and finds that 85 paid at the pump.

a. Estimate the population proportion.

b. Develop a 95% confidence interval for the population
proportion.
c. Interpret your findings.

© McGraw Hill 39
 Question 23 LO9-4

The attendance at the Savannah Colts minor league

baseball game last night was 400. A random sample of 50
of those in attendance revealed that the mean number of
soft drinks consumed per person was 1.86, with a standard
deviation of 0.50. Develop a 99% confidence interval for
the mean number of soft drinks consumed per person.

© McGraw Hill 40
 Question 25 LO9-5

A population’s standard deviation is 10. We want to

estimate the population mean with a margin of error of 2,
with a 95% level of confidence. How large a sample is
required?

© McGraw Hill 41
 Question 31 LO9-5

Suppose the U.S. president wants to estimate the

proportion of the population that supports his current policy
toward revisions in the health care system. The president
wants the margin of error to be 0.04. Assume a 95% level
of confidence. The president’s political advisors found a
similar survey from 2 years ago that reported that 60% of
people supported health care revisions.

a. How large of a sample is required?

b. How large of a sample would be necessary if no
estimate were available for the proportion supporting
current policy?

© McGraw Hill 42
 Because learning changes everything. ®

[Link]

© McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC.