SEC.

6-3: SAMPLING
DISTRIBUTIONS

Sec. 6-3: Sampling Distributions

Recall: While the population

mean is 𝜇, the sample mean is 𝑥̅ .

If several samples are drawn from

the same population, they are
likely to have different values for
𝑥̅ .

Sec. 6-3: Sampling Distributions

Because the value of 𝑥̅ varies each

time a sample is drawn, 𝑥̅ is a random
variable, and it has a probability
distribution.

Def. The probability distribution of 𝑥̅ is

called the sampling distribution of 𝑥̅ .

1
 Sec. 6-3: Sampling Distributions

Imagine that I tossed a 4-sided die

three times. The following table
summarizes the possible samples
that can occur, with their sample
means:

Sec. 6-3: Sampling Distributions

Sec. 6-3: Sampling Distributions

Notice: Some of the values for 𝑥̅

appear more than once, because
several samples have the same
mean.

2
 Sec. 6-3: Sampling Distributions

• The mean of the sampling distribution is

the average of these 64 values.

• The standard deviation of the sampling

distribution is the population standard
deviation of the 64 sample means.

We can compute these using the methods

we talked about in Chap. 3.

Sec. 6-3: Sampling Distributions

Result: The mean and standard

deviation for this sample distribution
are:

𝜇 ̅ = 2.5, 𝜎 ̅ = 0.6455

Recall: We can obtain these values

using the 1-Var Stats we learned in
Chap.3.

Sec. 6-3: Sampling Distributions

Comparing the mean and standard

deviation of the sampling distribution to the
mean and standard deviation of the
population, we notice the following:

• The mean of the sampling distribution is

equal to the population mean, ie, 𝜇 ̅ = 𝜇.

3
 Sec. 6-3: Sampling Distributions

Result: The mean and standard deviation are:

𝜇 ̅ = 2.5, 𝜎 ̅ = 0.6455

• The standard deviation of the sampling

distribution at 0.6455 is slightly less than the
population standard deviation of 𝜎 = 1.118.

• But!

.
• 𝜎 ̅ = 0.6455 = = . (Recall that n is the
sample size.)

Sec. 6-3: Sampling Distributions

Summary

• Let 𝑥̅ be the mean of a simple random sample

of size n, drawn from a population with mean
𝜇 and standard deviation 𝜎.

• The mean of the sampling distribution is the

same as the population mean. 𝜇 ̅ = 𝜇 .

• The standard deviation of the sampling

distribution is 𝜎 ̅ = .

Sec. 6-3: Sampling Distributions

• The standard deviation 𝜎 ̅ is

sometimes called the
standard error of the mean.

• (On the Chapter 6 in-class

assignment, “Standard Error”
is NOT a correct answer.)

4
 Sec. 6-3: Sampling Distributions

How do I know when to use

𝜎 and when to use 𝜎 ̅ ?

• Use 𝜎 for a population,

just like always.

• Use 𝜎 ̅ = for a sample.

Sec. 6-3: Sampling Distributions

(Ex) Suppose that an airline uses a seat width of 16.4

inches. Assume men have hip breadths that are
normally distributed with a mean 14.6 inches and a
standard deviation of 1 inch.

a) Find the probability that if an individual man is

randomly selected, his hip breadth will be greater
than 16.4 inches.

𝑃 𝑋 > 16.4

= 𝑛𝑜𝑟𝑚𝑎𝑙𝑐𝑑𝑓 16.4, 9999, 14.6, 1

0.0359

Sec. 6-3: Sampling Distributions

(Ex) Suppose that an airline uses a seat width of 16.4
inches. Assume men have hip breadths that are
normally distributed with a mean 14.6 inches and a
standard deviation of 1 inch.

b) If a plane is filled with 115 randomly selected men,

find the probability that these men have a mean hip
breadth greater than 16.4 inches.

𝑃 𝑋 > 16.4

= 𝑛𝑜𝑟𝑚𝑎𝑙𝑐𝑑𝑓 16.4, 9999, 14.6, 1/ 115

0.0000

5
 Sec. 6-3: Sampling Distributions

(Ex) Suppose that an airline uses a seat width of

16.4 inches. Assume men have hip breadths
that are normally distributed with a mean 14.6
inches and a standard deviation of 1 inch.

c) Which result should be considered for any

changes in seat design: the result from part
(a) or part (b)?

The result from part (a) should be considered

because the seats are occupied by individuals
rather than means.

Sec. 6-3: Sampling Distributions

Let’s switch gears and talk

about proportions.

Sec. 6-3: Sampling Distributions

Say a computer retailer wants to estimate

the proportion of people in her city who
own laptop computers. She cannot survey
everyone in the city, so she draws a
sample of 100 people and surveys them.

It turns out that 35 out of the 100 people in

the sample own laptops.

6
 Sec. 6-3: Sampling Distributions

The proportion 35⁄100 is called the

sample proportion and is called 𝑝.

The proportion of people in the entire

population who own laptops is called
the population proportion and is
denoted p.

Sec. 6-3: Sampling Distributions

Def. In a population, the

proportion who have a certain
characteristic is called the
population proportion, p.

Sec. 6-3: Sampling Distributions

In a simple random sample of n

individuals, let x be the number in the
sample who have the characteristic.

The sample proportion is 𝑝 = .

7
 Sec. 6-3: Sampling Distributions

Notation:

• The population proportion is

denoted by p.

• The sample proportion is

denoted by 𝑝̂ .

Sec. 6-3: Sampling Distributions

Mean and Standard Deviation of a Sample
Proportion

Let 𝑝̂ be the sample proportion of a simple random

sample of size n, drawn from a population with
population proportion p.

The mean and standard deviation of the sample

distribution of 𝑝̂ are:

𝜇 =𝑝

𝑝𝑞
𝜎 =
𝑛

Sec. 6-3: Sampling Distributions

(Ex) The soft drink cups at a certain fast food restaurant
have tickets attached to them. Customers peel off the
tickets to see whether they win a prize. The proportion of
tickets that are winners is 𝑝 = 0.25. A total of 𝑛 = 70
people purchase soft drinks between noon and 1:00pm
on a certain day.

Let 𝑝̂ be the proportion of customers that win a

prize. Find the probability that less than 23% of
customers during that time period won the prize.

Recall: Since we’re finding a probability, we need:

𝑛𝑜𝑟𝑚𝑎𝑙𝑐𝑑𝑓(𝑙𝑜𝑤𝑒𝑟, 𝑢𝑝𝑝𝑒𝑟, 𝜇, 𝜎)

8
 Sec. 6-3: Sampling Distributions

(Ex) The soft drink cups at a certain fast food

restaurant have tickets attached to them.
Customers peel off the tickets to see whether
they win a prize. The proportion of tickets that
are winners is 𝑝 = 0.25. A total of 𝑛 = 70 people
purchase soft drinks between noon and 1:00pm
on a certain day.

Let 𝑝̂ be the proportion of customers that win a

prize. Find the probability that less than 23% of
customers during that time period won the prize.

Mean: 𝜇 = 𝑝
0.25

Sec. 6-3: Sampling Distributions

(Ex) The soft drink cups at a certain fast food restaurant
have tickets attached to them. Customers peel off the
tickets to see whether they win a prize. The proportion of
tickets that are winners is 𝑝 = 0.25. A total of 𝑛 = 70 people
purchase soft drinks between noon and 1:00pm on a certain
day.
Let 𝑝 be the proportion of customers that win a prize.
Find the probability that less than 23% of customers
during that time period won the prize.
Standard Devation: 𝜎 =

Wait. If p is the population proportion and n is the sample

size, what’s q?

Recall, from Chapter 5: 𝑞 = 1 − 𝑝

Sec. 6-3: Sampling Distributions

(Ex) The soft drink cups at a certain fast food restaurant have
tickets attached to them. Customers peel off the tickets to see
whether they win a prize. The proportion of tickets that are
winners is 𝑝 = 0.25. A total of 𝑛 = 70 people purchase soft drinks
between noon and 1:00pm on a certain day.
Let 𝑝 be the proportion of customers that win a prize. Find
the probability that less than 23% of customers during that time
period won the prize.
Standard Devation: 𝜎 =

0.25 0.75
=
70

0.1875
= ≈ 0.0518
70

9
 Sec. 6-3: Sampling Distributions
(Ex) The soft drink cups at a certain fast food restaurant have
tickets attached to them. Customers peel off the tickets to see
whether they win a prize. The proportion of tickets that are
winners is 𝑝 = 0.25. A total of 𝑛 = 70 people purchase soft drinks
between noon and 1:00pm on a certain day.

Let 𝑝 be the proportion of customers that win a prize. Find the

probability that less than 23% of customers during that time period
won the prize.

𝑛𝑜𝑟𝑚𝑎𝑙𝑐𝑑𝑓(−9999, 0.23, 0.25, 0.0518)

≈ 0.3497

Sec. 6-3: Sampling Distributions

(Ex) The soft drink cups at a certain fast food restaurant
have tickets attached to them. Customers peel off the
tickets to see whether they win a prize. The proportion of
tickets that are winners is 𝑝 = 0.25. A total of 𝑛 = 70
people purchase soft drinks between noon and 1:00pm
on a certain day.

Question: How did I know that this situation called for a

proportion with 𝜇 = 𝑝 and 𝜎 = ,

instead of a situation with a sample where 𝜇 ̅ = 𝜇 and

𝜎̅= ?

Sec. 6-3: Sampling Distributions

(Ex) The soft drink cups at a certain fast food restaurant
have tickets attached to them. Customers peel off the
tickets to see whether they win a prize. The proportion of
tickets that are winners is 𝑝 = 0.25. A total of 𝑛 = 70
people purchase soft drinks between noon and 1:00pm
on a certain day.

Answer: Notice that nowhere in the problem is a mean or

standard deviation stated.

In general, in this class, if a mean and standard deviation

are not mentioned, that’s how you know you have a
proportion.

10
 Sec. 6-3: Sampling Distributions

We Covered:

• Sampling Distribution of a Sample Mean

• Proportions

Next section: The Central Limit Theorem

11