Chapter

8
Estimating Proportions
with Confidence

Section 8.2
Estimating a Population
Proportion
Estimating a Population
Proportion
LEARNING TARGETS
By the end of this section, you should be able to:
STATE and CHECK the Random, 10%, and Large Counts conditions
for constructing a confidence interval for a population
proportion.
DETERMINE the critical value for calculating a C% confidence
interval for a population proportion using a table or technology.
CONSTRUCT and INTERPRET a confidence interval for a
population proportion.
DETERMINE the sample size required to obtain a C% confidence
interval for a population proportion with a specified margin of
error.

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
One-Sample z Interval for a Population Proportion
When the conditions are met, a C% confidence interval for the unknown
proportion p is

where z* is the critical value for the standard Normal curve with C% of its
area between –z* and z*. This is called a one-sample z interval for a
population proportion.

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
There are three conditions that must be met for this formula to be valid—
one for each of the three components in the formula.

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
There are three conditions that must be met for this formula to be valid—
one for each of the three components in the formula.

1. The Random Condition

To be sure that is a valid point estimate, we check the Random
condition: The data come from a random sample from the population
of interest.

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
There are three conditions that must be met for this formula to be valid—
one for each of the three components in the formula.

2. The Large Counts Condition

When the Large Counts condition is met, we can use a Normal
distribution to calculate the critical value z* for any confidence level.
We don’t know the value of p, so we replace p by in checking the
Large Counts condition: and .
Starnes/Tabor, The Practice of Statistics
Constructing a Confidence
Interval for p
There are three conditions that must be met for this formula to be valid—
one for each of the three components in the formula.

3. The 10% Condition

Whenever we are sampling without replacement—which is nearly
always—we need to check the 10% condition: n < 0.10N, where n is the
sample size and N is the population size. Because we don’t know the
value of p, we replace it with the sample proportion .
Starnes/Tabor, The Practice of Statistics
Constructing a Confidence
Interval for p
When the standard deviation of a statistic is estimated from data, the
result is called the standard error of the statistic.

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
When the standard deviation of a statistic is estimated from data, the
result is called the standard error of the statistic.

In AP Statistics, confidence intervals come in the form

point estimate ± margin of error

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
When the standard deviation of a statistic is estimated from data, the
result is called the standard error of the statistic.

In AP Statistics, confidence intervals come in the form

point estimate ± margin of error

An equivalent form is
statistic ± (critical value)·(standard error of statistic)

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p

Conditions for Constructing a Confidence Interval

about a Proportion
• Random: The data come from a random sample from the population of
interest.
o 10%: When sampling without replacement, n < 0.10N.
• Large Counts: Both and are at least 10.

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
Problem: Mr. Buckley’s class wants to construct a confidence
interval for p = the true proportion of red beads in the

Studioshots/Alamy
container, which includes 3000 beads. Recall that the
class’s sample of 251 beads had 107 red beads and 144 other
beads. Check if the conditions for constructing a confidence
interval for p are met.

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
Problem: Mr. Buckley’s class wants to construct a confidence
interval for p = the true proportion of red beads in the

Studioshots/Alamy
container, which includes 3000 beads. Recall that the
class’s sample of 251 beads had 107 red beads and 144 other
beads. Check if the conditions for constructing a confidence
interval for p are met.

• Random: The class took a random sample of 251 beads from

the container. ✓

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
Problem: Mr. Buckley’s class wants to construct a confidence
interval for p = the true proportion of red beads in the

Studioshots/Alamy
container, which includes 3000 beads. Recall that the
class’s sample of 251 beads had 107 red beads and 144 other
beads. Check if the conditions for constructing a confidence
interval for p are met.

• Random: The class took a random sample of 251 beads from

the container. ✓
º 10%: 251 beads is less than 10% of 3000. ✓

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
Problem: Mr. Buckley’s class wants to construct a confidence
interval for p = the true proportion of red beads in the

Studioshots/Alamy
container, which includes 3000 beads. Recall that the
class’s sample of 251 beads had 107 red beads and 144 other
beads. Check if the conditions for constructing a confidence
interval for p are met.

• Random: The class took a random sample of 251 beads from

the container. ✓
º 10%: 251 beads is less than 10% of 3000. ✓
• Large Counts:

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
How do we get the critical value z* for our confidence interval?

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
How do we get the critical value z* for our confidence interval?

Finding the critical value z* for a 95%

confidence interval starts by labeling the
middle 95% under a standard Normal
curve and calculating the area in each tail.

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
How do we get the critical value z* for our confidence interval?

Finding the critical value z* for a 95%

confidence interval starts by labeling the
middle 95% under a standard Normal
curve and calculating the area in each tail.

Using Table A: Search the body of

Table A to find the point –z* with
area 0.025 to its left. The entry z =
– 1.96 is what we are looking for,
so z* = 1.96.

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
How do we get the critical value z* for our confidence interval?

Finding the critical value z* for a 95%

confidence interval starts by labeling the
middle 95% under a standard Normal
curve and calculating the area in each tail.

Using Table A: Search the body of

Table A to find the point –z* with
area 0.025 to its left. The entry z =
– 1.96 is what we are looking for,
so z* = 1.96.

Using technology: The command

invNorm(area:0.025, mean:0, SD:1)
gives z = –1.960, so z* = 1.960.
Starnes/Tabor, The Practice of Statistics
Constructing a Confidence
Interval for p
Problem: According to a 2016 Pew Research Center report,

Lisa Solonynko/Alamy
73% of American adults have read a book in the previous
12 months. This estimate was based on a random sample
of 1520 American adults. Assume the conditions for
inference are met.
(a) Determine the critical value z* for a 90% confidence interval for a proportion.
(b) Construct a 90% confidence interval for the proportion of all American adults
who have read a book in the previous 12 months.
(c) Interpret the interval from part (b).

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
Problem: According to a 2016 Pew Research Center report,

Lisa Solonynko/Alamy
73% of American adults have read a book in the previous
12 months. This estimate was based on a random sample
of 1520 American adults. Assume the conditions for
inference are met.
(a) Determine the critical value z* for a 90% confidence interval for a proportion.
(b) Construct a 90% confidence interval for the proportion of all American adults
who have read a book in the previous 12 months.
(c) Interpret the interval from part (b).

(a) Using Table A: z* = 1.64 or z* = 1.65

Using technology: invNorm (area:0.05, mean:0, SD:1) = –1.645,
so z* = 1.645.

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
Problem: According to a 2016 Pew Research Center report,

Lisa Solonynko/Alamy
73% of American adults have read a book in the previous
12 months. This estimate was based on a random sample
of 1520 American adults. Assume the conditions for
inference are met.
(a) Determine the critical value z* for a 90% confidence interval for a proportion.
(b) Construct a 90% confidence interval for the proportion of all American adults
who have read a book in the previous 12 months.
(c) Interpret the interval from part (b).

(b)

Starnes/Tabor, The Practice of Statistics

Constructing a Confidence
Interval for p
Problem: According to a 2016 Pew Research Center report,

Lisa Solonynko/Alamy
73% of American adults have read a book in the previous
12 months. This estimate was based on a random sample
of 1520 American adults. Assume the conditions for
inference are met.
(a) Determine the critical value z* for a 90% confidence interval for a proportion.
(b) Construct a 90% confidence interval for the proportion of all American adults
who have read a book in the previous 12 months.
(c) Interpret the interval from part (b).

(c) We are 90% confident that the interval from 0.711 to 0.749 captures p
5 the true proportion of American adults who have read a book in the
previous 12 months.

Starnes/Tabor, The Practice of Statistics

Putting It All Together: The Four-Step
Process

Confidence Intervals: A Four-Step Process

State: State the parameter you want to estimate and the confidence level.
Plan: Identify the appropriate inference method and check conditions.
Do: If the conditions are met, perform calculations.
Conclude: Interpret your interval in the context of the problem.

Starnes/Tabor, The Practice of Statistics

Putting It All Together: The Four-Step
Process
Problem: A recent poll of 738 randomly selected cell-phone users found
that 170 of the respondents admitted to walking into something or someone
while talking on their cell phone. Construct and interpret a 95% confidence
interval for the proportion of all cell-phone users who would admit to walking
into something or someone while talking on their cell phone.

Starnes/Tabor, The Practice of Statistics

Putting It All Together: The Four-Step
Process
Problem: A recent poll of 738 randomly selected cell-phone users found
that 170 of the respondents admitted to walking into something or someone
while talking on their cell phone. Construct and interpret a 95% confidence
interval for the proportion of all cell-phone users who would admit to walking
into something or someone while talking on their cell phone.

STATE:
95% CI for p = the true proportion of all cell-phone
users who would admit to walking into something or
someone while talking on their cell phone.

Starnes/Tabor, The Practice of Statistics

Putting It All Together: The Four-Step
Process
Problem: A recent poll of 738 randomly selected cell-phone users found
that 170 of the respondents admitted to walking into something or someone
while talking on their cell phone. Construct and interpret a 95% confidence
interval for the proportion of all cell-phone users who would admit to walking
into something or someone while talking on their cell phone.

PLAN:
One-sample z interval for p.
• Random: Random sample of 738 cell-phone users. ✓
º 10%: It is reasonable to assume that 738 is less than 10% of all
cell-phone users. ✓
• Large Counts: The number of successes (170) and the number of
failures (738 – 170 = 568) are both at least 10. ✓

Starnes/Tabor, The Practice of Statistics

Putting It All Together: The Four-Step
Process
Problem: A recent poll of 738 randomly selected cell-phone users found
that 170 of the respondents admitted to walking into something or someone
while talking on their cell phone. Construct and interpret a 95% confidence
interval for the proportion of all cell-phone users who would admit to walking
into something or someone while talking on their cell phone.

DO:

Starnes/Tabor, The Practice of Statistics

Putting It All Together: The Four-Step
Process
Problem: A recent poll of 738 randomly selected cell-phone users found
that 170 of the respondents admitted to walking into something or someone
while talking on their cell phone. Construct and interpret a 95% confidence
interval for the proportion of all cell-phone users who would admit to walking
into something or someone while talking on their cell phone.

CONCLUDE: We are 95% confident that the interval from

0.200 to 0.260 captures p = the true proportion of all
cell-phone users who would admit to walking into something
or someone while talking on their cell phone.

Starnes/Tabor, The Practice of Statistics

Putting It All Together: The Four-Step
Process
AP® Exam Tip
If a free response question asks you to construct and interpret a
confidence interval, you are expected to do the entire four-step process.
That includes clearly defining the parameter, identifying the procedure,
and checking conditions.

Starnes/Tabor, The Practice of Statistics

Putting It All Together: The Four-Step
Process
AP® Exam Tip
If a free response question asks you to construct and interpret a
confidence interval, you are expected to do the entire four-step process.
That includes clearly defining the parameter, identifying the procedure,
and checking conditions.

CAUTION:
Remember that the margin of error in a confidence interval only
accounts for sampling variability!

Starnes/Tabor, The Practice of Statistics

Choosing the Sample Size
In planning a study, we may want to choose a
sample size that allows us to estimate a population
proportion within a given margin of error.

Starnes/Tabor, The Practice of Statistics

Choosing the Sample Size
In planning a study, we may want to choose a
sample size that allows us to estimate a population
proportion within a given margin of error.

The formula for the margin of error

(ME) in the confidence interval for p is

Starnes/Tabor, The Practice of Statistics

Choosing the Sample Size
In planning a study, we may want to choose a
sample size that allows us to estimate a population
proportion within a given margin of error.

The formula for the margin of error

(ME) in the confidence interval for p is

To calculate the sample size, substitute

values for ME, z*, and , and solve for n.

Starnes/Tabor, The Practice of Statistics

Choosing the Sample Size

We won’t know the value of until after the study has been conducted.
This means we have to guess the value of when choosing n. Here are two
ways to do this:

Starnes/Tabor, The Practice of Statistics

Choosing the Sample Size

We won’t know the value of until after the study has been conducted.
This means we have to guess the value of when choosing n. Here are two
ways to do this:
1. Use a guess for based on a pilot (preliminary) study or past
experience with similar studies.

Starnes/Tabor, The Practice of Statistics

Choosing the Sample Size

We won’t know the value of until after the study has been conducted.
This means we have to guess the value of when choosing n. Here are two
ways to do this:
1. Use a guess for based on a pilot (preliminary) study or past
experience with similar studies.
2. Use = 0.5 as the guess. The margin of error ME is largest when = 0.5,
so this guess is conservative. If we get any other when we do our
study, the margin of error will be smaller than planned.

Starnes/Tabor, The Practice of Statistics

Choosing the Sample Size

Sample Size for Desired Margin of Error

when Estimating p
To determine the sample size n that will yield a C% confidence interval for
a population proportion p with a maximum margin of error ME, solve the
following inequality for n:

where is a guessed value for the sample proportion. The margin of error
will always be less than or equal to ME if you use = 0.5.

Starnes/Tabor, The Practice of Statistics

Choosing the Sample Size
Problem: A company has received complaints about its customer service. The
managers intend to hire a consultant to carry out a survey of customers. Before
contacting the consultant, the company president wants some idea of the sample
size that she will be required to pay for. One value of interest is the proportion p of
customers who are satisfied with the company’s customer service. She decides
that she wants the estimate to be within 3 percentage points (0.03) at a 95%
confidence level. How large a sample is needed?

wbritten/Getty Images
Starnes/Tabor, The Practice of Statistics
Choosing the Sample Size
Problem: A company has received complaints about its customer service. The
managers intend to hire a consultant to carry out a survey of customers. Before
contacting the consultant, the company president wants some idea of the sample
size that she will be required to pay for. One value of interest is the proportion p of
customers who are satisfied with the company’s customer service. She decides
that she wants the estimate to be within 3 percentage points (0.03) at a 95%
confidence level. How large a sample is needed?

1.96
√
0.5 (1− 0.5 )
≤ 0.03

wbritten/Getty Images
𝑛
Starnes/Tabor, The Practice of Statistics
Choosing the Sample Size
Problem: A company has received complaints about its customer service. The
managers intend to hire a consultant to carry out a survey of customers. Before
contacting the consultant, the company president wants some idea of the sample
size that she will be required to pay for. One value of interest is the proportion p of
customers who are satisfied with the company’s customer service. She decides
that she wants the estimate to be within 3 percentage points (0.03) at a 95%
confidence level. How large a sample is needed?

wbritten/Getty Images
Starnes/Tabor, The Practice of Statistics
Choosing the Sample Size
Problem: A company has received complaints about its customer service. The
managers intend to hire a consultant to carry out a survey of customers. Before
contacting the consultant, the company president wants some idea of the sample
size that she will be required to pay for. One value of interest is the proportion p of
customers who are satisfied with the company’s customer service. She decides
that she wants the estimate to be within 3 percentage points (0.03) at a 95%
confidence level. How large a sample is needed?

wbritten/Getty Images
Starnes/Tabor, The Practice of Statistics
Choosing the Sample Size
Problem: A company has received complaints about its customer service. The
managers intend to hire a consultant to carry out a survey of customers. Before
contacting the consultant, the company president wants some idea of the sample
size that she will be required to pay for. One value of interest is the proportion p of
customers who are satisfied with the company’s customer service. She decides
that she wants the estimate to be within 3 percentage points (0.03) at a 95%
confidence level. How large a sample is needed?

wbritten/Getty Images
Starnes/Tabor, The Practice of Statistics
Choosing the Sample Size
Problem: A company has received complaints about its customer service. The
managers intend to hire a consultant to carry out a survey of customers. Before
contacting the consultant, the company president wants some idea of the sample
size that she will be required to pay for. One value of interest is the proportion p of
customers who are satisfied with the company’s customer service. She decides
that she wants the estimate to be within 3 percentage points (0.03) at a 95%
confidence level. How large a sample is needed?

wbritten/Getty Images
Starnes/Tabor, The Practice of Statistics
Choosing the Sample Size
Problem: A company has received complaints about its customer service. The
managers intend to hire a consultant to carry out a survey of customers. Before
contacting the consultant, the company president wants some idea of the sample
size that she will be required to pay for. One value of interest is the proportion p of
customers who are satisfied with the company’s customer service. She decides
that she wants the estimate to be within 3 percentage points (0.03) at a 95%
confidence level. How large a sample is needed?

wbritten/Getty Images
Starnes/Tabor, The Practice of Statistics
Choosing the Sample Size
Problem: A company has received complaints about its customer service. The
managers intend to hire a consultant to carry out a survey of customers. Before
contacting the consultant, the company president wants some idea of the sample
size that she will be required to pay for. One value of interest is the proportion p of
customers who are satisfied with the company’s customer service. She decides
that she wants the estimate to be within 3 percentage points (0.03) at a 95%
confidence level. How large a sample is needed?

The sample needs to include at least 1068 customers.

(Why not round to the nearest whole number—in

this case, 1067? Because a smaller sample size
will result in a larger margin of error,

wbritten/Getty Images
possibly more than the desired 3 percentage
points for the poll.)

Starnes/Tabor, The Practice of Statistics

Section Summary

LEARNING TARGETS
After this section, you should be able to:
STATE and CHECK the Random, 10%, and Large Counts conditions
for constructing a confidence interval for a population
proportion.
DETERMINE the critical value for calculating a C% confidence
interval for a population proportion using a table or technology.
CONSTRUCT and INTERPRET a confidence interval for a
population proportion.
DETERMINE the sample size required to obtain a C% confidence
interval for a population proportion with a specified margin of
error.

Starnes/Tabor, The Practice of Statistics