Sampling Distribution

Lecture notes on Probability and Statistics
Instructor: Dr. K. M. Salah Uddin, Associate Professor

Department of Management Information Systems, University of Dhaka
Sampling Distribution
Sampling is only a tool which helps to know the characteristics of the
universe or population by examining only a small part of it. The values
obtained from the study of sample, such as average and variance, are
known as statistic. On the other hand, such values for the population
are called parameters.
If we take numerous different samples of equal size from the same

population, the probability distribution of all the possible values of a
given from all the distinct possible samples of equal size is called a
sampling distribution.
Note: The mean of the sampling distribution is designated by the same
symbol as the mean of the population namely, . However, the standard
deviation of the sampling distribution of means given a special name
standard error of mean, and is symbolized by
SAMPLING DISTRIBUTION OF THE MEAN

Problem:Prove that, the mean of the sampling distribution of the

sample mean is the same as the mean of the population.
Proof:
Let, x1, x2, ,xn represent independent variables corresponding to
the n observations in a sample from a population having the same mean
.
x1 x2 x3 ............................ xn
n
x1 x2 x3 ............................ xn
E ( x) E
1
E[ x1 ] E[ x2 ] .............................. E[ xn ]
n
1
1
................. .n
n
n
Problem:Prove that the variance of the sampling distribution of the
sample mean is the standard error of the mean.

Proof: Let, x1, x2, ,xn represent independent random variables

corresponding to the n observations in a sample from a population
having the same variance
x 2 Var x Var[
x1 x2 x3 ............................ xn
]
n
1
Var x1 Var x2 .................. Var xn
2
n
1 2
2
2
..........
..........
..
n2
1
2 n 2
n
1
2
n
x
n
which is the standard error of the mean.
Problem 01: The time between two arrivals in a queuing model is

normally distributed with a mean 2 minutes and the standard deviation
is 0.25 minute. If a random sample of size 36 is drawn, what is the
probability that sample mean is greater than 2.1 minutes?

Solution: Since the population is normally distributed, therefore, the

sampling distribution of the sample mean will also follow a normal
distribution with mean.
x 2
And standard error (standard deviation of sampling distribution)
0.25
0.042
n
36
Therefore, the probability that the sample mean will be greater than 2.1
minutes is given by
p[ x 2.1]
To get the values standard normal distribution, this normal variate

must be converted into a standard normal variate by the transformation
x x
z
x
Therefore, the above probability statement becomes

P[
x 2.1
]
x
x
P[ z
Or,
Or,
2.1 2
]
0.042
p[ z 2.38] 0.5 ( 2.38) 0.5 0.4913 0.0087
Therefore, in only 0.87% of all possible sample size n=36, the sample
mean will be greater than 2.1 minutes.
SAMPLING DISTRIBUTION OF THE DIFFERENCE OF TWO

MEANS
Suppose we have two populations, the first of size N1, with mean 1 and
standard deviation 1, and the second of size N2, with mean 2 and
standard deviation 2. The comparison is made on the basis of two
independent random samples, with one of size n1 drawn from the first
population and the other of size n2drawn from the second population. If

x1
x2
and
are the t wo sample means, we can evaluate the possible
difference between1 and 2, by the difference of the sample means
x1 x 2
The problem is one of determining the properties of a
sampling distribution of
x1 x 2
Important properties of the sampling distribution of
x1 x 2
are:
1. With simple random sampling from two independent populations,

the mean of the sampling distribution of
x1 x 2
i.e.,
x1 x 2
, deonted by
is equal to the difference between the population means,
x1 x 2 x1 x 2 1 2
=

2. The standard deviation of the sampling distribution of

(also known as standard error of
x1 x 2
(since
x1
and
x1
x2
x2
x1 x 2
x1 x 2
) is given by
21 2 2
n1
n2
are independent random variables, the variance of
their difference is the sum of their variances.)

Problem 02: Strength of the wire produced by company A has a
mean of 4500 kg and a standard deviation of 200 kg. Company B
has a mean of 4000 kg and a standard deviation of 300 kg. If 50
wires of company A and 100 wires of company B are selected at
random and tested for strength, what is the probability that the
sample mean strength of A will be at least 600kg more than B?
# For the sampling distribution of the difference of two means, we
have
x1 x 2 1 2 4500 4000 500

x1 x 2
21 2 2
40000 90000
800 900
n1
n2
50
100
1700 41.23

The desired probability is given by
P[ x1 x 2 600]
To convert this into standard normal variate, we get
x1 x 2 1 2 600 1 2
x1 x 2
x1 x 2
600 500
P Z
P[ Z 2.43]
41.23
0.5 2.43 0.5 0.4925 0.0075
Or,
Therefore, the probability that the sample mean strength of the
wire produced by company A is greater than or equal to 600 kg
than that of company B is given by 0.0075.
SAMPLING
DISTRIBUTION
SUCCESSES
OF
THE
NUMBER
OF
SAMPLING DISTRIBUTION OF PROPORTIONS

A population proportion is defined as
X / N,
where X is the number
of elements which process a certain trait and N is the total number of

items in the population. A sample proportion is defined as p=x/n, where

x is the number of items in the sample which process a certain trait and
n is the sample size.
Suppose that a population is infinite and that the probability of
occurrence of an event (called its success) is
non-occurrence of the event is
while the probability of
. Now consider all possible
samples of size n drawn from this population and for each sample
determine the proportion p of success. Then we obtain a sampling
distribution of sample proportion whose mean is p and standard
deviation p are given by:
p ; and p
(1 )
n
Where p=standard error of sample proportion. For large values of n

(n30) the sampling distribution is very closely approximated as
normally distributed.
Problem 03: In a quality department of manufacturing paints, at the
dispatch of decorative paints, 30% of the containers are found to be
defective. If a random sample of 500 is drawn with replacement from the

population, what is the probability that the sample proportion will be

less than or equal to 25% defective?
Solution:
We have,
p 0.3
p
And
(1 )
0 .3 0 .7
0.0205
n
500
The desired probability is given by P(p0.25)

To convert this into standard normal variate, we have
p p
0.25 0.3
P[ Z 2.44] 0.5 2.44

0.0205
0.5 0.4927 0.0073

Therefore, the required probability is 0.0073 that sample proportion will be less or
equal to 25% defective.
SAMPLING DISTRIBUTION OF THE DIFFERENCE OF TWO

PROPORTIONS
The sampling distribution of difference of two proportions can be
obtained from binomially distributed populations with parameter
and

respectively, when two random samples are drawn from two
binomial populations and then compared.
The mean and standard
deviation of this sampling distribution is given below:
p1 p2 p1 p2 1 2
and
p1 p2 2 p1 2 p2
1 1 1 2 1 2
n1
n2
If n1 andn2 large (n1, n230), the sampling distribution of difference of

two proportions are very closely normally distributed.
Problem 04: Ten percent of machines by company A are defective and

five percent of those produced by company B are defective. A random
sample of 250 machines is taken from company A and a random sample
of 300 machines from company B. what is the probability that the
difference in sample proportion is less than or equal 0.02?
Solution:
Under the assumption, the sampling distribution of p 1-p2 would have
mean

p1 p2 p1 p2 1 2
10
5
0.1 0.05 0.05

100 100
And standard deviation
p1 p2
1 1 1 2 1 2
n1
n2
0.1 0.9 0.05 0.95

0.09 0.0475
250
300
250
300
0.00036 0.00016 0.0228
The probability that the difference in sample proportion is less than or equal to 0.02
is given by
P(p1-p20.02)
Hence, the required probability is obtained by transforming into a

standard normal variate as,
p1 p2 p1 p2
0.02 0.05
0.0228
p1 p2
or, P z 1.32 0.5 1.32 0.5 0.4066 0.0934

Therefore, the required probability is 0.0934 that the difference ins
ample proportion is less than or equal to 0.02.

Sampling: Shoppers often sample a small piece of cheese before

purchasing any. They decide from one piece what the large will taste
like. A chemist does the same thing when he takes a sample of alcholo
from a still, determine that it is 90 proof and infers that all the in the still
is 90 proof.
A probability distribution of all the possible means of the samples is a

distribution of the sample means. Statisticians call this a sampling
distribution of mean.

Sampling Distribution

Uploaded by

Copyright:

Available Formats

Sampling Distribution

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Sampling Distribution

Uploaded by

Copyright:

Available Formats

Lecture notes on Probability and Statistics

Instructor: Dr. K. M. Salah Uddin, Associate Professor

If we take numerous different samples of equal size from the same