Professional Documents
Culture Documents
6.sampling Distribution
6.sampling Distribution
Introduction
• In real life calculating parameters of populations is
usually impossible because populations are very
large.
• Rather than investigating the whole population,
we take a sample, calculate a statistic related to
the parameter of interest, and make an inference.
• The sampling distribution of the statistic is the
tool that tells us how close is the statistic to the
parameter.
2
Sampling Distribution of the Mean
• An example
– A die is thrown infinitely many times. Let X
represent the number of spots showing on any
throw.
– The probability distribution of X is
E(X) = 1(1/6) +
x 1 2 3 4 5 6 2(1/6) + 3(1/6)+
………………….= 3.5
p(x) 1/6 1/6 1/6 1/6 1/6 1/6
V(X) = (1-3.5)2(1/6) +
(2-3.5)2(1/6) +
3
Throwing a die twice – sample mean
4
Throwing a die twice – sample mean
Sample
Sample Mean Sample
Mean Sample Mean Sample
Mean Sample Mean
Mean
11 1,1
1,1 11 13
13 3,1
3,1 22 25
25 5,1
5,1 33
22 1,2
1,2 1.5
1.5 14
14 3,2
3,2 2.5
2.5 26
26 5,2
5,2 3.5
3.5
33 1,3
1,3 22 15
15 3,3
3,3 33 27
27 5,3
5,3 44
44 1,4
1,4 2.5
2.5 16
16 3,4
3,4 3.5
3.5 28
28 5,4
5,4 4.5
4.5
55 1,5
1,5 33 17
17 3,5
3,5 44 29
29 5,5
5,5 55
66 1,6
1,6 3.5
3.5 18
18 3,6
3,6 4.5
4.5 30
30 5,6
5,6 5.5
5.5
77 2,1
2,1 1.5
1.5 19
19 4,1
4,1 2.5
2.5 31
31 6,1
6,1 3.5
3.5
88 2,2
2,2 22 20
20 4,2
4,2 33 32
32 6,2
6,2 44
99 2,3
2,3 2.5
2.5 21
21 4,3
4,3 3.5
3.5 33
33 6,3
6,3 4.5
4.5
10
10 2,4
2,4 33 22
22 4,4
4,4 44 34
34 6,4
6,4 55
11
11 2,5
2,5 3.5
3.5 23
23 4,5
4,5 4.5
4.5 35
35 6,5
6,5 5.5
5.5
12
12 2,6
2,6 44 24
24 4,6
4,6 55 36
36 6,6
6,6 66
5
Sample
Sample Mean Sample
Mean Sample Mean Sample
Mean Sample Mean
Mean
11
22
1,1
1,1
The distribution of1,2
1,2
11
1.5
1.5
13
13
14
14
3,1
X
3,1 22
3,2 2.5
3,2
25
25
when n = 2
2.5 26
26
5,1
5,1
5,2
5,2
33
3.5
3.5
33 1,3
1,3 22 15
15 3,3
3,3 33 27
27 5,3
5,3 44
44 1,4
1,4 2.5
2.5 16
16 3,4 3.5
3,4 3.5 28
28 5,4
5,4 4.5
4.5
55 1,5 33 17 3,5 44 29 5,5 22 55
1,5 17 3,5 29 5,5
66 1,6 3.5 18 3,6 4.5
4.5 302 5,6
5,6 x 5.5
5.5
77Note:: and
Note
1,6
2,1
2,1
3.5
1.5
1.5 and
x
18
19
19
3,6
4,1 2.5
4,1
x
2.5
30
31
31
2
x
6,1
6,1
x 3.5
3.5
22 x 20 x4,2 33 32x
88
99
2,2
2,2
2,3
2,3 2.5
2.5
20
21
21
4,2
22
4,3 3.5
4,3 3.5
32
33
33
6,2
6,2
6,3
6,3
44
4.5
4.5
10
10 2,4
2,4 33 22
22 4,4
4,4 44 34
34 6,4
6,4 55
11
11 2,5
2,5 3.5
3.5 23
23 4,5 4.5
4,5 4.5 35
35 6,5
6,5 5.5
5.5
12
12 2,6
2,6 44 24
24 4,6
4,6 55 36
36 6,6
6,6 66
E( x) =1.0(1/36)+
6/36 1.5(2/36)+….=3.5
5/36
7
Sampling Distribution of the Mean
n5 n 10 n 25
x 3.5 x 3.5 x 3.5
2x 2x 2x
x .5833 ( )
2 .2917 ( )
2
x .1167 ( )
2
x
5 10 25
Notice
Noticethat that x2 is
is smaller than .x.2
smaller than
Thelarger
The largerthethesample
samplesize sizethe
the
Therefore,x xtends
2
smaller x .. Therefore,
smaller tends
totofall closertoto,,asasthe
fallcloser thesample
sample
sizeincreases.
size increases. 8
SAMPLING DISTRIBUTION
• Let X1, X2,…,Xn be a r.s. of size n from a
population and let T(x1,x2,…,xn) be a real (or
vector-valued) function whose domain includes
the sample space of (X1, X2,…,Xn). Then, the
r.v. or a random vector Y=T(X1, X2,…,Xn) is
called a statistic. The probability distribution of
a statistic Y is called the sampling distribution
of Y.
9
SAMPLING DISTRIBUTION
• The sample mean is the arithmetic average of
the values in a r.s.
X1 X 2 X n 1 n
X Xi
n n i 1
• The sample variance is the statistic defined by
1 n
Xi X
2
S
2
n 1 i1
• The sample standard deviation is the statistic
defined by S.
10
SAMPLING FROM THE NORMAL
DISTRIBUTION
Properties of the Sample Mean and Sample
Variance
• Let X1, X2,…,Xn be a r.s. of size n from a
N(,2) distribution. Then,
2
a ) X and S are independent rvs.
b) X ~ N , / n
2
c)
n 1 S
2
~ n1
2
2
11
SAMPLING FROM THE NORMAL
DISTRIBUTION
• Let X1, X2,…,Xn be a r.s. of size n from a
N(,2) distribution. Then,
X
~ N 0,1
/ n
•Most of the time is unknown, so we use:
X
.
S/ n
12
SAMPLING FROM THE NORMAL
DISTRIBUTION
13
SAMPLING FROM THE NORMAL
DISTRIBUTION
• Let X1, X2,…,Xn be a r.s. of size n from a
N(X,X2) distribution and let Y1,Y2,…,Ym
be a r.s. of size m from an independent
N(Y,Y2).
• If we are interested in comparing the
variability of the populations, one
quantity of interest would be the ratio
X / Y S X / SY
2 2 2 2
14
SAMPLING FROM THE NORMAL
DISTRIBUTION
• The F distribution allows us to compare these
quantities by giving the distribution of
S X2 / SY2 S X2 / X2
2 2 ~ Fn1,m1
X / Y SY / Y
2 2
15
CENTRAL LIMIT THEOREM
If a random sample is drawn from any population, the sampling
distribution of the sample mean is approximately normal for
a sufficiently large sample size. The larger the sample size,
the more closely the sampling distribution of X will resemble
a normal distribution.
Random Sample
(X1, X2, X3, …,Xn)
X X
as n
Random Variable Sample Mean
(Population) Distribution Distribution
16
Sampling Distribution of the Sample
Mean
X
2
X
2
or X
n n
If X is normal, X is normal. If X is non-normal,
X is approximately normally distributed for
sample size greater than or equal to 30.
X
X ~ N( , / n ) Z
2
~ N( 0,1 )
/ n 17
EXAMPLE 1
• The amount of soda pop in each bottle is normally
distributed with a mean of 32.2 ounces and a
standard deviation of 0.3 ounces.
– Find the probability that a bottle bought by a customer
will contain more than 32 ounces.
– Solution
• The random variable X is the
amount of soda in a bottle. 0.7486
x 32 32.2
P( x 32) P( )
x .3 x = 32 = 32.2
P( z .67 ) 0.7486 18
EXAMPLE 1 (contd.)
x 32 32.2
P( x 32) P( ) 0.9082
x .3 4
P( z 1.33 ) 0.9082
0.7486
x = 32
x 32 = 32.2
x 32.2 19
Sampling Distribution of
a Proportion
^p = X
The estimate of p = n
20
Sampling Distribution of
a Proportion
21
Approximate Sampling Distribution of a
Sample Proportion
22
EXAMPLE
– A state representative received 52% of the
votes in the last election.
– One year later the representative wanted to
study his popularity.
– If his popularity has not changed, what is the
probability that more than half of a sample of
300 voters would vote for him?
23
EXAMPLE (contd.)
Solution
• The number of respondents who prefer the representative is
binomial with n = 300 and p = .52. Thus, np = 300(.52) = 156 and
n(1-p) = 300(1-.52) = 144 (both greater than 5)
pˆ p .50 .52
P ( pˆ .50) P .7549
p(1 p) n (.52)(1 .52) 300
24