SAMPLING DISTRIBUTION

Chapter 8
 WHY SAMPLE THE POPULATION?

 The physical impossibility of checking all items in the population.

 The cost of studying all the items in a population.
 The sample results are usually adequate.
 Contacting the whole population would often be time-consuming.
 The destructive nature of certain tests.

Sample the A probability sampling

Population
A non probability sampling
SAMPLING DISTRIBUTION
THE SAMPLING DISTRIBUTION

Use sample to infer to the population

 THE SAMPLING DISTRIBUTION
 Population  Sample
A numerical feature of a population is A statistic is a numerical valued
called a parameter. function of the sample observations.

Population distribution = probability

distribution from the information of all
elements of a population.
THE SAMPLING DISTRIBUTION OF STATISTIC

 In any statistic, the sample mean will vary from sample to sample as the
sampling process is repeated.

 It is a random variable and has its own probability distribution.

 The variability of statistic, in repeated sampling, is described by this

probability distribution.

The probability distribution of a statistics is called its

sampling distribution.
IF THE POPULATION IS NORMAL

If a population is normal with mean μ and standard deviation σ, the sampling

distribution of x is also normally distributed with
σ
μ μ
With replacement
σx 
x n
σ
Mean of the sampling mean σx 
n Without replacement

• Standard deviation of the sampling mean

• Standard error of the sampling mean
Z-VALUE FOR SAMPLING DISTRIBUTION OF x

Ch.7 Ch.8
Normal Probability distribution Sampling distribution

(x  μ)
z
σx
SAMPLING DISTRIBUTION PROPERTIES

μx  μ
(i.e. x is unbiased)
IF THE POPULATION IS NOT NORMAL

 We can apply the Central Limit Theorem:

 Even if the population is not normal,
 …sample means from the population will be approximately normal as
long as the sample size is large enough
THE CENTRAL LIMIT THEOREM APPLIES TO SAMPLING
DISTRIBUTIONS FROM ANY POPULATION
THE CENTRAL LIMIT THEOREM APPLIES TO SAMPLING
DISTRIBUTIONS FROM ANY POPULATION
CENTRAL LIMIT THEOREM

n↑
the sampling
As the
distribution
sample
becomes
size gets
almost
large
normal
enough
regardless of
…
shape of
population

x
 IF THE POPULATION IS NOT NORMAL
Population Distribution
Sampling distribution properties:

Central
Tendency
μx  μ
μ x
Variation σ Sampling Distribution
σx  (becomes normal as n increases)
n
Smaller Larger
sample size sample
(Sampling with replacement) size

μx x
SUMMARIZE SAMPLING DISTRIBUTION OF x

Chapter 7: Normal distribution

Chapter 8: Sampling distribution

μx  μ
With replacement
• Use when N is unknown and draw sampling
from Normal distribution
• Use when N is known and n ≤ 5% of N

Without replacement
• Use when N is known and n > 5% of N
Example 1: Random sample size of 50 students are taken from unknown size of
population, with a mean of 5 and variance of 100. The distribution of the population is
unknown.

a) Is the sampling distribution of the sample means approximately normal? If

yes, please give the reason why?

Answer ……….., the sampling distribution is approximately normal.

Because central limit theorem explain that when the sample size is
……………………………, the sampling distribution of mean will be
approximately normal.
Example 1: Random sample size of 50 students are taken from unknown size
of population, with a mean of 5 and variance of 100. The distribution of the
population is unknown.

b) What is the mean and the standard deviation of the sampling

distribution?
Example 2: A sample of 20 family were randomly selected from a normal population which
means age were 35 years old and standard deviation of 2.5 years old.

a) Is the sampling distribution of the sample means normally distributed? If yes,

please give the reason why?

Answer …………………., the sampling distribution of the sample mean is

normally distributed because the population is ………………………….
Example 2: A sample of 20 family were randomly selected from a normal
population which means age were 35 years old and standard deviation of 2.5
years old.

b) What is the mean and the standard error of the sampling distribution?
Example 3: The mean deposits at ABC Bank are $7,012 with a standard deviation of $532 and
they are normally distributed. If a random sample of 35 deposits is randomly selected, what is
the probability that the mean of this sample will be at least $6,911 ?

7,012
Example 4: The mean and standard deviation of the strength of a packaging material are 55
pounds and 7 pounds, respectively. If 40 pieces of the material are selected at random, find the
probability that the sample mean strength will be between 54 and 56 pounds ?

55
Example 5: According to the growth chart that doctors use as a reference, the heights of two-
year-old boys are normally distributed with mean 34.5 inches and standard deviation 1.3
inches. For a random sample of 6 two-year-old boys,

find the probability that the sample mean will be between 34.1 and 35.2 inches.

34.5

0
Example 6: Suppose that the weights of the people in a certain office building are
normally distributed, with a mean of 150 pounds and a standard deviation of 20
pounds. Suppose the elevator has a weight-sensitive safety switch and will not move if
the load exceeds 2,300 pounds. A randomly selected group of 16 crams into the
elevator at the close of business, what is the probability that the elevator will stop ?

0
SAMPLING DISTRIBUTION OF
SAMPLE PROPORTION
DISTINGUISH BETWEEN MEAN AND
PROPORTION

1. Wimon surveyed 100 students and asked them how many hours a
week they used their mobile phone?...........................................

2. Billy surveyed 250 students and asked them whether they used their
mobile phone for more than 6 hours per week?.............................

3. 50 randomly selected customers were asked “from 100% satisfaction,

please rate company ABC’s service”…………………

4. From sample of 150 new cars, at least 50 owners feel happy about
their cars………………….
SAMPLING DISTRIBUTION OF P
CENTRAL LIMIT THEOREM FOR SAMPLE
PROPORTION
Sampling Distribution P( p )

 Approximated by a .3
.2
normal distribution if: .1
0
 0 .2 .4 .6 8 1 p

With replacement
• Use when N is unknown and draw sampling
from Normal distribution
• Use when N is known and n ≤ 5% of N

Without replacement
• Use when N is known and n > 5% of N
Example 1: The following raw data represent the respondent from the
question of “Do you like sherbet ice cream?”, sampling from 32 teenagers.
Y Y Y N N N Y Y N N Y N Y N Y N Y Y Y N
Y Y Y Y Y N N N N N N Y

Y=
If the population proportion who like sherbet ice cream is 0.5
N=
a) What is the sample proportion of teenagers who like the sherbet ice cream?
Example 1: The following raw data represent the respondent from the
question of “Do you like sherbet ice cream?”, sampling from 32 teenagers.
If the population proportion who like sherbet ice cream is 0.5

b) What is the standard error of the sampling distribution of the sampling distribution of
sample proportions?
Example 2: All medium-and large-sized corporations showed that 64% of them offer
retirement plans for their employees. In a random sample of 50, find the probability that
percentage of corporations that offer retirement plans to their employees will be greater
than 70% ?

0.64
p
z
0
Example 3: A city is planning to build a hydroelectric power plant. A local newspaper
found that 53% of the voters in this city favor the construction of this plant. Assume that
this result holds true for the population of all voters in this city. What is the probability
that more than 50% of the voters in a random sample of 200 voters selected from this
city will favor the construction of this plant?

p
0.53
z
0
Example 4: If it is known that the true proportion of all manufactured
components made by a firm that are defective is 4%, find the probability
that a random sample of size 60 will have fewer than 3% defective
components.

0.04
p
z
0