Lecture 28 - Central Limit Theorem Examples

Central Limit Theorem Examples
Lecture 28
Sections 8.2, 8.4
Robb T. Koether
Hampden-Sydney College
Wed, Oct 12, 2011
Robb T. Koether (Hampden-Sydney College) Central Limit Theorem Examples Wed, Oct 12, 2011 1 / 42
Outline
1 The Sampling Distribution of x
2 The Central Limit Theorem for Means
3 Applications
Sampling Distribution of x
Probability Concerning x
Hypothesis Tests Concerning x
4 Assignment
Outline
3 Applications
4 Assignment
The Population
We will continue with our population consists of 100 people, 20%

of whom weigh 60 lbs, 20% of whom weigh 120 lbs, and 60% of
whom weigh 180 lbs.
Then the mean of the population is
µ = 144
and the standard deviation is
σ = 48.
Select One Person
Select one person at random.

What are the possibilities?
Sample Size n = 1
We can summarize this in a table.

x P(x)
60 0.20
120 0.20
180 0.60
µ = 144, σ = 48
Sample Size n = 2
Now take a sample of 2 people.

Find the sampling distribution of x.
Sample Size n = 2
The sampling distribution of x is

x P(x)
60 0.04
90 0.08
120 0.28
150 0.24
180 0.36
µx = 144, and σx = 33.94.
Sample Size n = 3
Now take a sample of 3 people.

Find the sampling distribution of x.
Sample Size n = 3
The sampling distribution of x is

x P(x)
60 0.008
80 0.024
100 0.096
120 0.152
140 0.288
160 0.216
180 0.216
µx = 144, and σx = 27.21.
Sample Size n = 4
When n = 4, the sampling distribution of x is

x P(x )
60 0.0016
75 0.0064
90 0.0288
105 0.0640
120 0.1456
135 0.1920
150 0.2592
165 0.1728
180 0.1296
µx = 144, and σx = 24.
Sample Size n = 5

x P(x )
60 0.0003
72 0.0016
84 0.0080
96 0.0224
108 0.0592
120 0.1059
132 0.1776
144 0.2016
156 0.2160
168 0.1296
180 0.0778
µx = 144, and σx = 21.47.
Sample Size n = 6

x P(x )
60 0.0001
70 0.0004
80 0.0020
90 0.0070
100 0.0211
110 0.0465
120 0.0922
130 0.1394
140 0.1901
150 0.1901
160 0.1711
170 0.0933
180 0.0467
µx = 144, and σx = 19.60.
Sample Size n = 10

x P(x )
60 0.0000
66 0.0000
72 0.0000
78 0.0000
84 0.0002
90 0.0006
96 0.0019
102 0.0050
108 0.0119
114 0.0245
120 0.0452
126 0.0735
132 0.1069
138 0.1362
144 0.1540
150 0.1496
156 0.1265
162 0.0873
168 0.0504
174 0.0202
180 0.0060
µx = 144, and σx = 15.18.

Outline
3 Applications
4 Assignment
The Sample Mean
Definition (Sampling Distribution of x)

Thesampling distribution of x is the probability distribution of x over all
possible samples of a given size n.
The symbol µ represents the population mean.

The symbol x represents a samplemean.
So x is a random variable because its value varies from sample to
sample.
The Central Limit Theorem for Means
Theorem (The Central Limit Theorem for Means)

For any population with mean µ and standard deviation σ, thesampling
distribution of x has the following mean and standarddeviation:
µx = µ
σ
σx = √ .
n
Furthermore, if the population is normal, then x is normal.

If the population is not normal, but n ≥ 30, then x is approximately
normal.
The Central Limit Theorem for Means
The Central Limit Theorem for Means describes the distribution of

x in terms of µ, σ, and n.
A problem may ask about a single observation, or it may ask
about the sample mean in a sample of observations.
If it asks about a single observation, then do not try to use the
Central Limit Theorem.
However, if it asks about a sample mean, then you must use the
Central Limit Theorem.
Outline
3 Applications
4 Assignment
Outline
3 Applications
4 Assignment
Outline
3 Applications
4 Assignment
Applications
Example 8.10, page 540.

Let X be the length of a pregnancy in days. Thus, X is a continuous
random variable. Suppose that it has approximately a normal
distribution with a mean of 266 days and a standard deviation of 16
days.
(a)Sketch the distribution for X .
Applications

Let X be the length of a pregnancy in days. Thus, X is a continuous
random variable. Suppose that it has approximately a normal
distribution with a mean of 266 days and a standard deviation of 16
days.
(a)Sketch the distribution for X .
0.025
0.020
0.015
0.010
0.005
240 260 280 300
Applications

(b)Suppose that we have a random sample of n = 25 pregnant
women. Describe the sampling distribution of x .
Applications

(b)Suppose that we have a random sample of n = 25 pregnant
women. Describe the sampling distribution of x .
It is normal with mean 266 and standard deviation
16
√ = 3.2.
25
Applications

(c)What is the probability that a randomly selected pregnancy lasts
more than 274 days?
Applications

(c)What is the probability that a randomly selected pregnancy lasts
more than 274 days?
normalcdf(274,E99,266,16) = 0.3086.
Applications

(c) What is the probability that a randomly selected pregnancy lasts
more than 274 days?
normalcdf(274,E99,266,16) = 0.3086.
(d) Is it more likely or less likely, as compared to part (c), that we might
observe a sample mean pregnancy length of more than 274 days?
Explain.
Applications

(c) What is the probability that a randomly selected pregnancy lasts
more than 274 days?
normalcdf(274,E99,266,16) = 0.3086.
(d) Is it more likely or less likely, as compared to part (c), that we might
observe a sample mean pregnancy length of more than 274 days?
Explain.
The probability is normalcdf(274,E99,266,3.2) = 0.0062,
which is much less. That is because the standard deviation is
smaller, pulling the values of x closer to themean.
Example
Exercise 8.43, page 560.

In human engineering and product design, it is important to consider
the weights of people so that airplanes or elevators aren’t overloaded.
Based on data from the National health Survey, the weight for adult
males in the United States follows a normal distribution with a mean
weight of 173 pounds and a standard deviation of 30 pounds.
(a)If one U.S. adult male is randomly selected, what is the probability
that his weight will be greater than 180 pounds?
Example

In human engineering and product design, it is important to consider
the weights of people so that airplanes or elevators aren’t overloaded.
Based on data from the National health Survey, the weight for adult
males in the United States follows a normal distribution with a mean
weight of 173 pounds and a standard deviation of 30 pounds.
(a)If one U.S. adult male is randomly selected, what is the probability
that his weight will be greater than 180 pounds?
normalcdf(180,E99,173,30) = 0.4077.
Example

(a)If 36 different U.S. adult males are randomly selected, what is the
probability that their sample mean weight will be greater than 180
pounds?
Example

pounds?
The distribution of x is normal with mean 173 and standard
deviation σx = √30 = 5.
36
Example

pounds?
The distribution of x is normal with mean 173 and standard
deviation σx = √30 = 5.
36
Therefore, the probability that x is greater than 180 is
normalcdf(180,E99,173,5) = 0.0808.
Outline
3 Applications
4 Assignment
Example
Example
A manufacturer of a particular model of car claims that the average
gas mileage for that model is 34 mpg. A consumer group suspects that
the gas mileage is not that high. They believe that it is only 32 mpg.
The standard deviation is assumed to be 3 mpg. An independent
researcher hopes to settle the question by testing a sample of 64
vehicles of that model. He will test the hypotheses
H0 : µ = 34
H1 : µ = 32
He will reject H0 if x < 33.
Example
Example
(a)Find α and β for this test.
Example
Example
(a)Find α and β for this test.
(b)What is the p-value of 33.5?
Outline
3 Applications
4 Assignment
Assignment
Homework
Read Section 8.4, pages 531 - 545.
Let’s Do It! 8.10.
Exercises 17 - 22, 24 - 26, 28, page 551.
Review exercises 33 - 38, 40, 41, 43 - 46, page 557.
Assignment
Answers
18.(a) N(69, 0.8333).
(b) N(69,0.25).
(c)The second one has a smaller standard deviation.
Assignment
Answers
20.
0.4
0.3
0.2
0.1
12 13 14 15 16 17
Assignment
Answers
22.(a)
0.4
0.3
0.2
0.1
26 27 28 29 30 31
Assignment
Answers
22.(a) (i)27 and 29.
(ii)26 and 30.
(iii)25 and 31.
Assignment
Answers
22.(c)
0.8
0.6
0.4
0.2
26 27 28 29 30 31
Assignment
Answers
22.(c) (i)It is narrower (twice as narrow).
(ii)It will be half as wide (27.5 to 28.5).
(d)No. A value of 26 mpg for x would be 4 standard
deviations below average.
Assignment
Answers
24.(a)
0.20
0.15
0.10
0.05
–6 –4 –2 2 4
Assignment
Answers
24.(b) (i)It is N(−1, 0.2).
2.0
1.5
1.0
0.5
(ii) –1.4 –1.2 –1.0 –0.8 –0.6 –0.4
(iii)0 .3085.
Assignment
Answers
26.(a)No. Only 1 /4 of the values are less than 4.
(b)No. The distribution is skewed, so the mean and
median are not equal.
(c)Histogram C. With a sample size of 500, the CLT
says that the shape of the distribution will be normal.
The other two histograms are clearly not normal.
Assignment
Answers
34.(a)Histogram C.
(b)(iii)
36.0 .9352.
38.Histogram A.
40.(a)100.
(b)400.
(c) 0.
(d) As the sample size increases, the accuracy of
a sample mean increases.
Assignment
Answers
44.(a)No. The probability of such an observation is 0 .1056,
which is not very small. Therefore, it is not unlikely
that it could happen by chance even if the mean
really is 750.
(b)2 standard deviations of x.
46.(a)0 .4772.
(b)0 .4226.

Lecture 28 - Central Limit Theorem Examples

Încărcat de

Informații document

Titlu original

Drepturi de autor

Formate disponibile

Partajați acest document

Partajați sau inserați document

Opțiuni de partajare

Vi se pare util acest document?

Este necorespunzător acest conținut?

Drepturi de autor:

Formate disponibile

Lecture 28 - Central Limit Theorem Examples

Încărcat de

Drepturi de autor:

Formate disponibile

Central Limit Theorem Examples

Wed, Oct 12, 2011

1 The Sampling Distribution of x

2 The Central Limit Theorem for Means

1 The Sampling Distribution of x

2 The Central Limit Theorem for Means

We will continue with our population consists of 100 people, 20%

and the standard deviation is

Select one person at random.

We can summarize this in a table.

Now take a sample of 2 people.

The sampling distribution of x is

Now take a sample of 3 people.

The sampling distribution of x is

When n = 4, the sampling distribution of x is

When n = 5, the sampling distribution of x is

When n = 6, the sampling distribution of x is

When n = 10, the sampling distribution of x is

µx = 144, and σx = 15.18.

1 The Sampling Distribution of x

2 The Central Limit Theorem for Means

Definition (Sampling Distribution of x)

The symbol µ represents the population mean.

Theorem (The Central Limit Theorem for Means)

Furthermore, if the population is normal, then x is normal.

The Central Limit Theorem for Means describes the distribution of

1 The Sampling Distribution of x

2 The Central Limit Theorem for Means

1 The Sampling Distribution of x

2 The Central Limit Theorem for Means

1 The Sampling Distribution of x

2 The Central Limit Theorem for Means

Example 8.10, page 540.

Example 8.10, page 540.

240 260 280 300

Example 8.10, page 540.

Example 8.10, page 540.

Example 8.10, page 540.

Example 8.10, page 540.

Example 8.10, page 540.

Example 8.10, page 540.

Exercise 8.43, page 560.

Exercise 8.43, page 560.

Exercise 8.43, page 560.

Exercise 8.43, page 560.

Exercise 8.43, page 560.

1 The Sampling Distribution of x

2 The Central Limit Theorem for Means

1 The Sampling Distribution of x

2 The Central Limit Theorem for Means

(ii) –1.4 –1.2 –1.0 –0.8 –0.6 –0.4

S-ar putea să vă placă și