Sampling distribution is a probability

distribution of a sample statistic based on all

possible simple random sample of the same
size from the same population.
Introduction to Sampling Distribution
1.5 Sampling Distribution
Sampling Distribution of Mean ( )
Institut Matematik Kejuruteraan, UniMAP
2
n
x
o
o =
Standard deviation of sampling distribution
=
x
Mean of sample mean ,
X
Mean of sampling distribution = mean of population
2
2
x
n
o
o =
Variance of sampling distribution
EQT 373
Central Limit Theorem
Institut Matematik Kejuruteraan, UniMAP
3
If we are sampling from a population that has an unknown
probability distribution, the sampling distribution of the
sample mean will still be approximately normal with mean
and standard deviation , if the sample size n is large.

n
o
EQT 373
Properties and shape of sampling
distribution of the sample mean
Institut Matematik Kejuruteraan, UniMAP
4
n 30 , the sampling distribution of the sample mean is normally
distributed
n < 30, the sampling distribution of the sample mean is normally
distributed if the sample is from the normal population and variance is
known
|
|
.
|

\
|
n
N x
2
, ~
o

|
|
.
|

\
|
n
N x
2
, ~
o

EQT 373
Institut Matematik Kejuruteraan, UniMAP
5
t-distribution with n-1 degree of freedomif the sample is fromthe
normal population but the variance is unknown and n<30
1
2
~

=
n
t
n
s
x
T

x
x
Z
o

=
The value of Z
EQT 373
Example
Institut Matematik Kejuruteraan, UniMAP
6
The amount of time required to change the oil and filter of
any vehicles is normally distributed with a mean of 45
minutes and a standard deviation of 10 minutes. A random
sample of 16 cars is selected.
What is the standard error of the sample mean to be?
What is the probability of the sample mean between 45 and 52
minutes?
What is the probability of the sample mean between 39 and 48
minutes?
Find the two values between the middle 95% of all sample
means.
EQT 373
Institut Matematik Kejuruteraan, UniMAP
7
( )
2
: the amount of time required to change the oil and filter of any vehicles
~ 45,10 16
X
X N n =
2
: the mean amount of time required to change the oil and filter of any vehicles
10
~ 45,
16
X
X N
| |
|
\ .
10
a) the standard error, 2.5
16
o = =
( )
( )
45 45 52 45
b) 45 52
2.5 2.5
0 2.8
0.4974
P X P Z
P Z

| |
< < = < <
|
\ .
= < <
=
EQT 373
Institut Matematik Kejuruteraan, UniMAP
8
( )
( )
39 45 48 45
c) 39 48
2.5 2.5
2.4 1.2
0.4918 0.3849
0.8767
P X P Z
P Z

| |
< < = < <
|
\ .
= < <
= +
=
( )
( )
d) 0.95
45 45
0.95
2.5 2.5
0.95
from table:
1.96
1.96
45
1.96 40.1
2.5
45
1.96 49.9
2.5
a b
a
b
P a X b
a b
P Z
P z Z z
z
z
a
a
b
b
< < =

| |
< < =
|
\ .
< < =
=
=

= =

= =
EQT 373
Sampling Distribution of the Sample
Proportion
Institut Matematik Kejuruteraan, UniMAP
9
where
N = total number of elements in the population;
X = number of elements in the population that possess a
specific characteristic;
n = total number of elements in the sample; and
x = number of elements in the sample that possess a specific
characteristic
X
p
N
=

x
p
n
= and
EQT 373
Sampling Distribution of Sample Proportion,
for Infinite Population
Institut Matematik Kejuruteraan, UniMAP
10
The probability distribution of the sample proportion , is
called its sampling distribution. It gives various values that
can assume and their probabilities.
For the large values of n (n 30), the sampling distribution is
very closely normally distributed.
Mean of the Sample Proportion
The mean of the sample proportion, is denoted by
and is equal to the population proportion, p.
p
p
=

p
p

p
p
p

EQT 373
Standard Deviation of the Sample
Proportion
Institut Matematik Kejuruteraan, UniMAP
11
where p is the population proportion, and n is the sample
size.
n
pq
p
=

o
(1 )

~ ,
p p
p N p
n

| |
|
\ .
EQT 373
Institut Matematik Kejuruteraan, UniMAP
12
For a small values of n:
the population is binomial distributed,
) , ( ~ p n B X
( )
x n x
x
n
q p C x X P
n
x
p P

= = =
|
.
|

\
|
=

( ) np X E mean = ,
( ) npq X Var =
p
p p
Z

= The value of Z :
EQT 373
Example
If the true proportion of voters who support Proposition A is
what is the probability that a sample of size 200 yields a sample proportion
between 0.40 and 0.45? If and n = 200, what is
?
0.40 p =
0.40 p =
( )
0.40 0.45 P p s s

(1 ) 0.4(1 0.4)
0.03464
200
p
p p
n

= = =
0.40 0.40 0.45 0.40
(0.40 0.45)
0.03464 0.03464
(0 1.44) 0.4251
P p P Z
P Z

| |
s s = s s
|
\ .
= s s =
13
Institut Matematik Kejuruteraan, UniMAP
EQT 373
Example
Institut Matematik Kejuruteraan, UniMAP
14
The National Survey of Engagement shows about 87% of
freshmen and seniors rate their college experience as good
or excellent. Assume this result is true for the current
population of freshmen and seniors. Let be the proportion of
freshmen and seniors in a random sample of 900 who hold
this view. Find the mean and standard deviation of . p
EQT 373
Solution:
Institut Matematik Kejuruteraan, UniMAP
15
Let p the proportion of all freshmen and seniors who rate their college
experience as good or excellent. Then,
p = 0.87 and q = 1 p = 1 0.87 = 0.13
The mean of the sample distribution of is: p
87 . 0

= = p
p

( )
011 . 0
900
13 . 0 87 . 0

=
=
=
p
p
p
n
pq
o
o
o
The standard deviation of : p
EQT 373
Sampling Distribution for the
Difference between Two Means
Institut Matematik Kejuruteraan, UniMAP
16
Suppose we have two populations, which are normally distributed and the
variance are known. If the variance are unknown, the sample size must be
large enough and the variance are estimated from
the sample.
2
1 1 1
~ ( , ) X N o
2
2 2 2
~ ( , ) X N o
and
Sampling distribution for :
|
|
.
|

\
|
1
2
1
1
1
, ~
n
N X
o

|
|
.
|

\
|
2
2
2
2
2
, ~
n
N X
o
and
1 2
and X X
1 2
( 30 and 30) n n > >
EQT 373
17
( )
( ) ( )
1 2
1 2
1 2
1 2


X X
E X X
E X E X

=
=
=
MEAN
VARIANCE
( ) ( ) ( )
( ) ( ) ( )
1 2 1 2
2
1 2
2 2
1 2
1 2
1

Var X X Var X Var X
Var X Var X
n n
o o
= +
= +
= +
Institut Matematik Kejuruteraan, UniMAP
EQT 373
18
2 2
1 2
1 2 1 2
1 2
~ , X X N
n n
o o

| |
+
|
\ .
Therefore the distribution of can be written as:
1 2
X X
( ) ( )
( )
1 2 1 2
2 2
1 2
1 2
~ 0,1
X X
Z N
n n

o o

=
+
Institut Matematik Kejuruteraan, UniMAP
EQT 373
Example:
A taxi company purchased two brands of tires, brand A and brand B. It is
known that the mean distance travelled before the tires wear out is 36300 km
for brand A with standard deviation of 200 km while the mean distance
travelled before the tires wear out is 36100 km for brand A with standard
deviation of 300 km. A random sample of 36 tires of brand A and 49 tires of
brand B are taken. What is the probability that the
a) difference between the mean distance travelled before the tires of brand
A and brand B wear out is at most 300 km?
b) mean distance travelled by tires with brand A is larger than the mean
distance travelled by tires with brand B before the tires wear out?
19
Institut Matematik Kejuruteraan, UniMAP
EQT 373
: the mean distance travelled before the tires of brand A wear out
: the mean distance travelled before the tires of brand B wear out
Solution:
( )
2 2
200 300
~ 36300 36100,
36 49
~ 200, 2947.846
A B
A B
X X N
X X N
| |
+
|
\ .

B
X
A
X
( ) ( )
( )
a) | | 300 300 300
300 200 300 200

2947.846 2947.846
9.21 1.84 0.9671
A B A B
P X X P X X
P Z
P Z
s = s s
| |
= s s
|
\ .
= s s =
( ) ( )
( )
b) 0
0 200

2947.846
3.68 0.9999
A B A B
P X X P X X
P Z
P Z
> = >
| |
= >
|
\ .
= > =
20
Institut Matematik Kejuruteraan, UniMAP
EQT 373
Sampling Distribution for the
Difference between Two Proportions
21
|
|
.
|

\
|

1
1 1
1 1
) 1 (
, ~

n
p p
p N P
|
|
.
|

\
|

2
2 2
2 2
) 1 (
, ~

n
p p
p N P
( )
( ) ( )
1 2
1 2
1 2
1 2

,



P P
mean E P P
E P E P
p p

=
=
=
Now say we have two binomial populations with proportion of successes and
2
p
1
p
Institut Matematik Kejuruteraan, UniMAP
EQT 373
22
|
|
.
|

\
|

+

2
2 2
1
1 1
2 1 2 1
) 1 ( ) 1 (
, ~

n
p p
n
p p
p p N P P
( )
( ) ( )
1 2
2
1 2
2
1 2
1 1 2 2
1 2


( 1)
(1 ) (1 )

P P
Var P P
Var P Var P
p p p p
n n
o

=
= +
| | | |

= +
| |
\ . \ .
Variance
Using the Central Limit Theorem, the distribution of is
1 2

P P
Institut Matematik Kejuruteraan, UniMAP
EQT 373
Example
Institut Matematik Kejuruteraan, UniMAP
23
A certain change in a process for manufacture of component parts
was considered. It was found that 75 out of 1500 items from the
existing procedure were found to be defective and 80 of 2000
items from the new procedure were found to be defective. If one
random sample of size 49 items were taken from the existing
procedure and a random sample of 64 items were taken from the
new procedure, what is the probability that
the proportion of the defective items from the new procedure
exceeds the proportion of the defective items from the existing
procedure?
proportions differ by at most 0.015?
the proportion of the defective items from the new procedure
exceeds proportion of the defective items from the existing
procedure by at least 0.02?
EQT 373
Institut Matematik Kejuruteraan, UniMAP
24

: the proportion of defective items from the new procedure

: the proportion of defective items from the existing procedure

80 75
0.04 0.05
2000 1500
N
E
N E
P
P
p p = = = =
0.04(0.96) 0.05(0.95)

~ 0.04, ~ 0.05,
64 49
N E
P N P N
| | | |
| |
\ . \ .
( )
0.05(0.95) 0.04(0.96)

~ 0.04 0.05,
49 64

~ 0.01, 0.0016
N E
N E
P P N
P P N
| |
+
|
\ .

Solution:
EQT 373
Institut Matematik Kejuruteraan, UniMAP
25
( ) ( )
( )
( )

a) 0
0 0.01

0.0016
0.25
0.4013
N E N E
P P P P P P
P Z
P Z
> = >
| |
= >
|
\ .
= >
=
( ) ( )
( ) ( )
( )

b) | | 0.015 0.015 0.015
0.015 0.01 0.015 0.01

0.0016 0.0016
0.125 0.625

N E N E
P P P P P P
P Z
P Z
s = s s
| |
= s s
|
\ .
= s s
0.2838 =
( ) ( )
( )
( )

c) 0.02 0.02
0.02 0.01

0.0016
0.75
0.2266
N E N E
P P P P P P
P Z
P Z
> = >
| |
= >
|
\ .
= >
=
EQT 373