7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Introduction
In module 4 you learned about the distribution of X where X is a continuous random variable that follows
the normal distribution. X could stand for age, salary, expenses, sales, profit, etc.
⎯
⎯
⎯⎯
In this module, you will learn about the sampling distribution of X (i.e., sample mean) and p (i.e., sample
proportion). These two distributions are the foundation of inferential statistics for the later modules where
you will learn about estimation and hypothesis testing.

With the inferential statistics, you take a sample data from a specific population and try to describe the
population in terms of mean or proportion depending on the type of data you collect. If you collect
quantitative data, then you would describe the population using mean. If you collect qualitative data, then
you would describe the population using proportion or percentage.

In general, it is very unlikely that the sample mean is equal to the population mean. The difference
between two measures will be quite close or far apart. But in inferential statistics, we need to measure
the exact difference and the sampling distribution provides this basis of calculation of differences.

Topics and Learning Objectives

Topics
Central Limit Theorem
Sampling Distribution of the Sample Mean
Sampling Distribution of the Sample Proportion

Learning Objectives
Upon successful completion of this module, you should be able to:

Explain the fundamental concepts of the Central Limit Theorem.

Calculate probabilities of interval events for sample means and sample totals.
Determine interval boundaries for sample means and sample totals.
Calculate probabilities of interval events for sample proportions.

Readings

Required Readings

[Link] 1/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

1. Study Online Module 5

2. Read and study Chapter 8 of the course e-textbook, available in MyLab.

Key Terms
Here is a list of key terms and concepts presented in this module, assigned readings, and resources. It is
important that you understand what they represent within the context of this course.

After studying the learning materials provided in this module, if you need clarification on any of these
terms, please ask your instructor for help.

Population Proportion
Is denoted as π

Sample proportion
Is denoted as p

Population Mean
Is denoted as μ

Sample Mean
⎯
⎯
⎯⎯
Is denoted as X

Normal Distribution
A bell-shaped distribution defined by its mean (μ) and standard deviation (σ).

Sampling Distribution of Sample Means

The probability distribution of the means from all possible samples of size nnn drawn from a population.

Sampling Distribution of Sample Proportions

The probability distribution of the proportions from all possible samples of size nnn drawn from a
population.

[Link] 2/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Central Limit Theorem

This theorem states that, in most situations, the sampling distribution of sample means will be
approximately normal when the sample size is greater than 30.

Sampling Distributions
There are two types of sampling distributions: (1) sampling distribution of sample means and (2)
sampling distribution of p, as shown in figure 1 below.

Figure 1: Types of sampling distributions

Long Description +

The diagram on the left-hand side showed how the sampling distribution of means could
be formed from the population. The process of constructing the distribution of sample
⎯
⎯
⎯⎯
⎯⎯
means involve a process of randomly selecting a sample, say n1, to calculate X1 .
⎯
⎯
⎯⎯
Whether with or without replacement, you draw another sample, say n2, to calculate X 2
⎯
⎯
⎯⎯
⎯⎯⎯
⎯
⎯⎯
⎯⎯
and so on. Use the sample mean values (X1 , X2 , etc.) to construct the distribution of
sample means. The diagram on the right-hand side showed how the sampling
distribution of proportions could be formed from reaching into the population. Randomly
select sample n1 to calculate the p1, sample n2 to calculate p2 and etc. Use the sample
proportions, p1, p2, p3, etc. to construct the distribution of p, where p denotes the
sample proportion. Note: p̂ also denotes sample proportion but in this course, we will use
p to represent the sample proportion.

[Link] 3/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Tab Panels (expanded):

Tab: Sampling Distribution of Means

⎯
⎯
⎯⎯
Sampling distribution of sample means (X )
Consider any population with mean, µ and standard deviation σ . All the possible samples of a
given size, say n, are taken. The mean of each of these samples may be calculated and denoted
⎯
⎯
⎯⎯
⎯⎯⎯
⎯
⎯⎯
⎯⎯⎯
⎯
⎯⎯
⎯⎯⎯
⎯
⎯⎯
⎯⎯⎯
⎯
⎯⎯
⎯⎯⎯
⎯
⎯⎯
⎯⎯
as X1 ,X2 ,X3 ,X4 ,X5 ,X6 ,…
⎯
⎯
⎯⎯
⎯⎯
The random variable X consists of all the possible XS . A corresponding probability
⎯
⎯
⎯⎯
⎯⎯
distribution of the XS exist.
The probability distribution of the sample means is called the Sampling distribution of the
sample means.
⎯
⎯
⎯⎯
The single result of X from one sample is taken from all possible samples in the sampling
distribution.

Consider any population of distribution X with mean, µ and standard deviation σ , the mean and
⎯
⎯
⎯⎯
standard deviation of the sampling distribution of X are as follows:
⎯
⎯
⎯⎯
The mean of the sampling distribution of X is μ⎯⎯⎯⎯ = μ.
X
⎯
⎯
⎯⎯
μX⎯⎯⎯⎯denotes the mean of the sampling distribution of X .
⎯
⎯
⎯⎯
Standard deviation of the sampling distribution of X is σ⎯⎯⎯⎯= σ .
X √
n
⎯
⎯
⎯⎯
σX⎯⎯⎯⎯denotes standard deviation of the sampling distribution of X , also known as standard
error of the mean.

⎯
⎯
⎯⎯
Most importantly, sampling distribution of X will be normally distributed if a random sample is
drawn from any population that is normally distributed and if not, a sufficiently large sample size
is required by the central limit theorem (i.e., n > 30).

Check-Up Time
1. The standard deviation of the sampling distribution of the mean is:
a. The standard error of the mean
b. The standard error times the sample size
c. 1
d. Approximately 68%
[Link] 4/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

e. Don't know

Check Your Answer

Tab: Sampling Distribution of Sample Proportions

Sampling distribution of sample proportions (p)

A repeated random sample of a given sample size, n, are taken from a population of X values
where X is a categorical variable representing the number of “success” (or category of interest).

Then use the value of X to calculate the sample proportion of “success”, p (where p = nx ).
The probability distribution of the sample proportions is called the Sampling distribution of
the sample proportions.

The sampling distribution of p follows the binomial distribution either with replacement or without
replacement for very large populations. The binomial distribution can be approximated to a
normal distribution if np ≥ 5 and n(1 − p) ≥ 5.

The mean of the sampling distribution of p is μp = π.

μp denotes the mean of the sampling distribution of p .

Standard deviation of the sampling distribution of p is σp = ‾π(1−π)

‾‾‾‾ ‾ .
√ n

σp denotes standard deviation of the sampling distribution of p, also known as standard

error of the proportion.

Check-Up Time
1. The standard deviation of the sampling distribution of the proportion is:
a. The standard error of the proportion
b. 1
c. The standard error times the sample size
d. Approximately 68%
e. Don’t know

[Link] 5/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Check Your Answer

Central Limit Theorem

The central limit theorem (CLT) is a set of three “facts” that relate to the distribution of sample means
and the original distribution being sampled. Imagine we took a sample from a normal distribution, like the
speed of cars on Highway 401 near Toronto. Compute the mean of the sample, x. Get another sample.
Compute its mean too. Continue to do this until you have a large number of sample means, xs. What do
we know about the collection of xs?

Fact 1
μX⎯⎯⎯⎯ = μ : The mean of ALL the sample means (µx) = the mean of the original population( µx).

Regardless of the sample size or any other characteristic of the original distribution, the mean of all the
sample means, µx, is the same as the mean of the original population, µ. If the population mean speed of
all the cars on the 401 is 110 km/hr, then the mean of all sample means (of any fixed size, n) is also 110
km/hr.

Fact 2
Standard error of the mean: σ⎯⎯⎯⎯= σ
X √
n

For large populations, the standard deviation of xs is proportional to the standard deviation of the original
distribution and inversely proportional to the square root of the sample size. If you double the standard
deviation of the original distribution being sampled, the distribution of sample means, xs, also doubles. If
the sample size, n, is 4, then the standard deviation distribution of sample means, σx, is half the standard
deviation of the original distribution being sampled. If the sample size, n, is 9, then the standard deviation
distribution of sample means, σx, is one-third the standard deviation of the original distribution being
sampled.

Fact 3
In most cases, the distribution of sample means, xs , is normal. Specifically, if the original distribution
being sampled is normal or the sample size, n, is greater than or equal to 30, then the distribution of
sample means, x, is normal.

To better understand the Central Limit Theorem and how the mean and standard deviation of the
sampling distribution are defined, please refer to Chapter 8, Section 8.2, and Figure 8.6 in the CQMS210
e-book.

[Link] 6/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Example CLT Questions

Question 1

Click-n-reveal: The Air Canada 8:15 am flight from Pearson International Airport in Toronto to
LaGuardia Airport in New York has an average time of one hour and twenty-five minutes, with a
standard deviation of 12 minutes. The distribution of times is unimodal but right skewed. What is
the probability that the mean time for the eighty-one flights from Toronto to New York scheduled
for this summer will be between 82 and 87 minutes?

x – time for Toronto to New York 8:15 am flight

x – mean time for sample of 81 such flights

x – normal (see Fact 2 of CLT), n ≥ 30

P(82 ≤ x ≤ 87) = { [STAT][DIST][NORM] “Ncd” “Variable”

Input Values:

Source: Toronto Metropolitan University

Long Description +

Normal C.D
Data: Variable
Lower: 82
Upper: 87
σ: 12÷√(81)
μ: 85
Save Res: None

[Link] 7/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction
σ 12
σX⎯⎯⎯⎯= n
, see Fact 3 of CLT = σX⎯⎯⎯⎯= 81
= 1.333333
√ √

µ = µx, see Fact 1 of CLT = 85

Results:

Source: Toronto Metropolitan University

Long Description +

Normal C.D
P = 0.92096832
z:Low = -2.25
z:Up = 1.5

⎯
⎯
⎯⎯
P (82 ≤ X ≤ 87) = 0.9210 (rounded to 4 decimal places)

Question 2

Click-n-reveal: What is the probability that the average time for the sixty-four 8:15 am flights from
Toronto to New York scheduled for this coming Fall will be over 86 minutes?

x - time for Toronto to New York 8:15 am flight

⎯
⎯
⎯
x - mean time for sample of 64 such flights
⎯
⎯
⎯
x - normal
⎯
⎯
⎯
P(x > 86) = {[STAT][DIST][NORM] “Ncd” “Variable”

[Link] 8/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

The calculator input:

Source: Toronto Metropolitan University

Long Description +

Normal C.D
Data: Variable
Lower: 86
Upper: 1E+12
σ: 12÷√(64)
μ: 85
Save Res: None

The result is:

Source: Toronto Metropolitan University

Long Description +

Normal C.D
P = 0.25249253
[Link] 9/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

z:Low = 0.66666666
z:Up = 6.6667E+11

⎯
⎯
⎯⎯
P (X > 86) = 0.2525

Question 3

Click-n-reveal: Every Spring, thirty-six 8:15 am flights from Toronto to New York are scheduled.
There is a 10% chance that the mean time for the Spring flights to arrive at New York was more
than ________ minutes.

x – time for Toronto to New York 8:15 am flight

x – mean time for sample of 36 such flights

x – normal (see Fact 3 of CLT), n ≥ 30

L={ [STAT][DIST][NORM] “InvN” ”Variable”

Input values:

Source: Toronto Metropolitan University

Long Description +

Inverse Normal
Data: Variable
Tail: Right
Area: 0.1
σ: 12÷√(36)

[Link] 10/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

μ: 85
Save Res: None

The result is:

Source: Toronto Metropolitan University

Long Description +

Inverse Normal
xInv = 87.5631031

Question 4

Click-n-reveal: 25% of the Spring flights will take less than what mean to arrive at New York? Hint:
This is an inverse normal question.

L = {[STAT][DIST][NORM] “InvN” ”Variable”

The calculator input:

Source: Toronto Metropolitan University

[Link] 11/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Long Description +

Inverse Normal
Data: Variable
Tail: Left
Area: 0.25
σ: 12÷√(36)
μ: 85
Save Res: None

The result is:

Source: Toronto Metropolitan University

Long Description +

Inverse Normal
xInv = 83.6510205

A Note
σ
σX⎯⎯⎯⎯= n
√

For large populations, the standard deviation of sample means does not depend on the
population size (i.e., no N in the relationship), so if the standard deviation of ages is similar in
both provinces, then both estimates have similar “accuracy.”

[Link] 12/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Module Summary
Key Summary Points
The probability distribution of the sample means is called the Sampling distribution of the
sample means.
The standard deviation of the sample means is called the Sampling error of the mean.
The probability distribution of the sample proportions is called the Sampling distribution of the
sample proportions.
⎯
⎯
⎯⎯
To calculate the probability of the sample average or sample mean (or denoted as X ), the
⎯
⎯
⎯⎯
sampling distribution of X has to be normally distributed. You can apply the Central Limit Theorem
⎯
⎯
⎯⎯
if the sampling distribution of X is not normally distributed and the sample size must exceed 30.
To calculate the probability of the sample “total”, you must first convert “sample total” to “sample
mean” and make sure the newly convert statistics is normally distributed. If not, you can apply the
central limit theorem.

Check Your Understanding

Example Problems

Tab Panels (expanded):

Tab: Probability Distribution of the Sample Means

Example problems on the probability distribution of the

sample means
Example Problem 1
Assume that a school district has 20,000 8th graders. In this district, the average weight of a 8th
grader is 95 pounds with a standard deviation of 15 pounds. Suppose you draw a random sample
of 64 students.

What is the probability that the average weight of a sample of students will be more than 100
pounds?

Click-n-reveal: Click here to see the solution to Example Problem 1

[Link] 13/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Solution:
⎯
⎯
⎯⎯ ⎯
⎯
⎯⎯ ⎯
⎯
⎯⎯
To find p(X > 100) we use the distribution of X where the mean of X is μX⎯⎯⎯⎯ = μ and
σ ⎯
⎯
⎯⎯
σX⎯⎯⎯⎯= n
Distribution of X is normal because sample size (n) is greater than 30, according
√

to the Central Limit Theorem

Using the CASIO calculator:

Select STAT F5(DIST; F1 (NORM); F2 (Ncd); F2 (Var);

Input the following data:

Source: Toronto Metropolitan University

Long Description +

Normal C.D
Data: Variable
Lower: 100
Upper: 100000
σ: 15÷√(64)
μ: 95
Save Res: None

⎯
⎯
⎯⎯
The answer for P(X > 100) = 0.0038 :

[Link] 14/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Source: Toronto Metropolitan University

Long Description +

Normal C.D
P = 3.8304e-03
z:Low = 2.66666667
z:Up = 53282.6667

Example Problem 2
Assume that a school district has 20,000 8th graders. In this district, the average weight of an 8th
grader is 95 pounds with a standard deviation of 15 pounds.

Suppose you draw a random sample of 64 students. What is the maximum average weight of the
lightest 25%?

Click-n-reveal: Click here to see the solution to Example Problem 2

Solution:
⎯
⎯
⎯⎯ ⎯
⎯
⎯⎯ ⎯
⎯
⎯⎯
To find X (average weight), we use the distribution of X where the mean of X is μ⎯⎯⎯⎯ = μ
X
σ ⎯
⎯
⎯⎯
and σ⎯⎯⎯⎯= Distribution of X is normal because sample size (n) is greater than 30,
X √
n
according to Central Limit Theorem

Using the CASIO calculator:

Select STAT F5(DIST); F1 (NORM); F3 (InvN); F2 (Var);

Input the following data:

[Link] 15/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Source: Toronto Metropolitan University

Long Description +

Inverse Normal
Data: Variable
Tail: Left
Area: 0.25
σ: 15÷√(64)
μ: 95
Save Res: None

The maximum average weight of the lightest 25% is 93.735.

The results on the calculator are:

Source: Toronto Metropolitan University

[Link] 16/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Long Description +

Inverse Normal
xInv = 93 7353317

Tab: Probability Distribution of the Sample Proportions

Example problems on the probability distribution of the

sample proportions
Example Problem 3
Suppose you surveyed 20 adults. If the population proportion of adults who like to shop online is
0.56, what is the probability that more than half in your sample prefer to shop online?

Click-n-reveal: Click here to see the solution to Example Problem 3

Solution:

To find P (p
> 0.5) use the distribution of p (sample proportion) where the mean of p is
μp = π and σp = √‾‾‾‾‾
π(1−π)‾
n
Distribution of p is normal as long as nπ ≥ 5 and
n(1 − π) > 5 are satisfied.
Using the CASIO calculator:

Select STAT F5(DIST); F1 (NORM); F3 (InvN); F2 (Var);

Input the following data:

[Link] 17/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Source: Toronto Metropolitan University

Long Description +

Normal C.D
Data: Variable
Lower: 0.5
Upper: 100
σ: 0.11099549
μ: 0.56
Save Res: None

The answer for P(p > 0.5) = 0.7056

See calculator results below:

Source: Toronto Metropolitan University

Long Description +

Normal C.D
P = 0.7055954
z:Low = -0.5405624
z:Up = 895.892213

[Link] 18/19
7/11/26, 7:55 PM CQMS210, Module 5 - Introduction

Assignments

Discussion Board
Note: this may be graded, please refer to course assessments as posted by the instructor.

Post your response to the question problem posted by the instructor in this week’s
Discussion Board.

Required

By 6:00 p.m. Wednesday of this module week, post your answer and a brief explanation of
how you arrived at the answer in this week’s Discussion Board.

Note: you can access the Discussions from the Communications menu in your D2L course.

e-homework
Note: this is a Graded Activity

Complete the Module 5 MyLab Statistics e-homework. See the D2L course section for
details.

The due date is indicated in the assignment.

[Link] 19/19