Probability and Statistics

Chapter 8
Sampling Distributions

Prepared by:
Dr. Walaa El Sharkawy
Contents

1. Basic Definitions.
2. Sampling Distribution.
3. ഥ.
Sampling Distribution of 𝑿
4. Sampling Distribution of Proportions.
5. t-Distribution, Chi-Square Distribution, and F Distribution.
 Basic Definitions
Statistical inference is concerned with making decisions about a population based on
the information contained in a random sample from that population.

Definitions:
1- Population consists of the totality of the observations with which we are concerned.
2- Sample is a subset of a population.
3- Parameter is a number that describes some characteristic of the population.
• Example: population mean, standard deviation, and proportion.
4- Statistic is a number that describes some characteristic of a sample.
• Example: sample mean, standard deviation, and proportion.
Basic Definitions
Notes:
In statistical practice,

➢ the value of a parameter is not known because we cannot examine the

entire population.

➢ The value of a statistic can be computed directly from the sample data,
but it can change from sample to sample. We often use a statistic to
estimate an unknown parameter.

➢ Sample must be representative of the population.

• Representative: The sample has the same characteristics as the
population.
• Samples are representative: If every case in the population has the
same chance of being selected.
Sampling Distribution

➢ Information from the sample is linked to the population via the sampling
distribution.
 Sampling Distribution
Definition:
The probability distribution of a statistic is called a sampling distribution.

For example, the probability distribution of 𝑋ത is called the sampling distribution

of the mean.

The sampling distribution of a statistic will depend on:

1. the distribution of population,
2. the size of the samples,
3. the method of choosing the random samples.
Sampling Distribution of 𝑿
ഥ

Steps for the construction of Sampling Distribution of the

mean
1- From a finite population of size N , randomly draw all possible samples of
size n .
2- Calculate the mean for each sample.
3- Summarize the mean obtained in step 2 in terms of frequency distribution
or relative frequency distribution
Sampling Distribution of 𝑿
ഥ

Example: Suppose there are only five students in an advanced statistics class
and the midterm scores of these five students are: 6, 8,10, 12, and 14.
Take samples of size 2 with replacement, then
1) construct sampling distribution of the sample mean.
2) find the mean and variance of population.
3) find the mean and variance of 𝑥.ҧ
Sampling Distribution of 𝑿
ഥ

Note:
let N =population size, n = sample size.
Suppose simple random sampling is used. We have
𝑁 𝑛 :possible samples if sampling is with replacement and with order.
𝐶𝑛𝑁 :possible samples if sampling is without replacement without order.
𝑃𝑛𝑁 :possible samples if sampling is without replacement with order.
Sampling Distribution of 𝑿
ഥ

Solution:
• 𝑁 = 5, 𝑛 = 2
• We have 𝑁 𝑛 = 52 = 25 possible samples since sampling is with
replacement.
Step 1: Draw all possible samples:
Sampling Distribution of 𝑿
ഥ
Solution:
Step 2: Calculate the mean for each sample:

Step 3: Summarize the mean obtained in step 2 in terms of frequency

distribution.
Sampling Distribution of 𝑿
ഥ
Solution:
• Mean and variance of population data:
σ𝑥
𝜇= = 10
𝑁
σ 𝑥−𝜇 2
2
𝜎 = =8
𝑁

• Mean and variance of 𝑥:ҧ

σ 𝑥ҧ
𝜇𝑥ҧ = 𝑛 = 10 = 𝜇
𝑁
ҧ 𝑥ഥ 2
σ 𝑥−𝜇 𝜎2 8
𝜎𝑥2ҧ = =4≠𝜎 2
but = =4
𝑁𝑛 𝑛 2
Sampling Distribution of 𝑿
ഥ
Solution:
 Sampling Distribution of 𝑿
ഥ
In general
➢ If sampling is with replacement from a finite population or with or without
replacement from an infinite population. Then
2
𝜎
𝜎𝑥2ҧ =
𝑛

𝜎 2 𝑁−𝑛
➢ Otherwise 𝜎𝑥2ҧ =
𝑛 𝑛−1

➢ If sampling is with replacement/ without replacement. Then

𝜇𝑥ҧ = 𝜇

Note: The square root of the variance of the sampling distribution 𝜎𝑥ҧ is called
the standard error.
 Sampling Distribution of 𝑿
ഥ
To generalize, we distinguish between two situations:

➢ sampling from a normally distributed population.

➢ sampling from a nonnormally distributed population.

Sampling Distribution of 𝑿
ഥ
When sampling is from a normally distributed population, the distribution of the
sample mean will possess the following properties:
1) The distribution of 𝑥ҧ will be normal.
2) 𝜇𝑥ҧ = 𝜇
2
2 𝜎
3) 𝜎𝑥ҧ =
𝑛

𝜎 2 ҧ
𝑥−𝜇
ത
That is, 𝑋~𝑁 𝜇, , then 𝑍 = 𝜎/ ~ 𝑁(0,1)
𝑛 𝑛
Sampling Distribution of 𝑿
ഥ
Population distribution and sampling distributions of 𝑥ҧ

Note:
The spread of the
sampling distribution of
decreases as the sample
size increases.
Sampling Distribution of 𝑿
ഥ
When sampling is from a nonnormally distributed population, we refer to an
important mathematical theorem known as the central limit theorem (CLT).
➢ According to the CLT, for a large sample size, the distribution of the
sample mean will possess the following properties:
1) The sampling distribution of 𝑥ҧ is approximately normal.
2) 𝜇𝑥ҧ = 𝜇
2
2 𝜎
3) 𝜎𝑥ҧ =
𝑛

𝜎 2 ҧ
𝑥−𝜇
ത
That is, 𝑋~𝑁 𝜇, , then 𝑍 = 𝜎/ ~ 𝑁(0,1)
𝑛 𝑛

Note: The sample size is usually considered to be large if n ≥ 30.

Sampling Distribution of 𝑿
ഥ
Population distribution and sampling distributions of 𝑥ҧ
Sampling Distribution
Example:
Assume that the weights of all packages of a certain brand of cookies are
normally distributed with a mean of 32 ounces and a standard deviation of 0.3
ounce. Find the probability that the mean weight, of a random sample of 20
packages of this brand of cookies will be less than 31.8 ounces.

Solution:
𝝈 𝟎.𝟑
𝝁𝑿ഥ = 𝝁 = 𝟑𝟐, and 𝝈𝑿ഥ = = = 𝟎. 𝟎𝟔𝟕𝟎𝟖
𝒏 𝟐𝟎

𝟑𝟏. 𝟖 − 𝟑𝟐
ഥ < 𝟑𝟏. 𝟖 = 𝑷 𝒁 <
𝑷 𝑿 = 𝑷 𝒁 < −𝟐. 𝟗𝟖 = 𝟎. 𝟎𝟎𝟏𝟒
𝟎. 𝟎𝟔𝟕𝟎𝟖
Sampling Distribution of 𝑿
ഥ
Example:
If the mean and standard deviation of serum iron values for healthy men are 120
and 15 micrograms per 100 ml, respectively, what is the probability that a
random sample of 50 men will yield a mean between 115 and 125 micrograms
per 100 ml?
Solution:
𝝈 𝟏𝟓
𝒏 = 𝟓𝟎 , 𝑭𝒓𝒐𝒎 𝑪𝑳𝑻 𝒕𝒉𝒆𝒏 𝝁𝑿ഥ = 𝝁 = 𝟏𝟐𝟎, and 𝝈𝑿ഥ = = =𝟑
𝒏 𝟓𝟎

𝟏𝟏𝟓 − 𝟏𝟐𝟎 𝟏𝟏𝟓 − 𝟏𝟐𝟓

ഥ ≤ 𝟏𝟐𝟓 = 𝑷
𝑷 𝟏𝟏𝟓 ≤ 𝑿 ≤ 𝒁≤
𝟑 𝟑
= 𝑷 −𝟐. 𝟑𝟔 ≤ 𝒁 ≤ 𝟐. 𝟑𝟔
= 𝑷 𝒁 ≤ 𝟐. 𝟑𝟔 − 𝑷(𝒁 ≤ −𝟐. 𝟑𝟔)
= 0.9909 − 0.0091
= 0.9818
 Sampling Distribution of 𝑿
ഥ
Summary:
ഥ
Sampling distribution of 𝑿

𝑿~𝑵(𝝁, 𝝈𝟐 ) 𝑿 𝑵𝒐𝒕~𝑵(𝝁, 𝝈𝟐 )

𝝈𝟐 is known 𝝈𝟐 is unknown 𝒏 ≥ 𝟑𝟎 𝒏 < 𝟑𝟎

𝒏 ≥ 𝟑𝟎 𝒏 < 𝟑𝟎
𝝈𝟐
ഥ ~𝑵(𝝁, )
𝑿 ??
𝒏
𝝈𝟐 𝒔𝟐
ഥ ~𝑵(𝝁,
𝑿 ) ഥ ~𝑵(𝝁,
𝑿 ) ഥ ~𝑻𝒗
𝑿
𝒏 𝒏
Sampling Distribution of 𝒑
ෝ
The population and sample proportions, denoted by p and 𝑝,Ƹ respectively,
are calculated as

X x
p= and pˆ =
N n
Where,
N = total number of elements in the population
n = total number of elements in the sample
X = number of elements in the population that possess a specific
characteristic
x = number of elements in the sample that possess a specific characteristic
Sampling Distribution of 𝒑
ෝ

When the sample size is large (𝑛𝑝 > 5 𝑎𝑛𝑑 𝑛 1 − 𝑝 > 5), the distribution of
sample proportions 𝑝Ƹ is approximately normally distributed by the central
limit theorem.

1) The mean of the distribution is 𝜇𝑝ො = 𝑝

𝑝(1−𝑝)
2) The variance of the distribution is 𝜎𝑝2ො =
𝑛

ො
𝑝−𝑝
Ƹ 𝑁(𝜇𝑝ො , 𝜎𝑝2ො ), then 𝑍 =
That is, 𝑝~
𝑝(1−𝑝)
𝑛
Sampling Distribution of 𝒑
ෝ
Example: Sample of 150 individuals from a population in which 35.7 percent
are obese. Find the probability that the value of 𝑝Ƹ is grater than 0.4.
Solution:
𝒏 = 𝟏𝟓𝟎, 𝒑 = 𝟎. 𝟑𝟓𝟕.
Here, 𝒏𝒑 = 𝟏𝟓𝟎 𝟎. 𝟑𝟓𝟕 = 𝟓𝟑. 𝟓𝟓 > 𝟓
𝒏 𝟏 − 𝒑 = 𝟏𝟓𝟎 𝟎. 𝟔𝟒𝟑 = 𝟗𝟔. 𝟒𝟓 > 𝟓
ෝ~ 𝑵(𝝁𝒑ෝ , 𝝈𝟐𝒑ෝ ),
Then from CLT, 𝒑

(𝟎.𝟑𝟓𝟕)(𝟎.𝟔𝟒𝟑)
where 𝝁𝒑ෝ = 𝟎. 𝟑𝟓𝟕 and 𝝈𝟐𝒑ෝ = = 0.00153.
𝟏𝟓𝟎

𝟎. 𝟒 − 𝟎. 𝟑𝟓𝟕
ෝ > 𝟎. 𝟒 = 𝑷 𝒁 >
𝑷 𝒑
0.00153
= 𝑷 𝒁 > 𝟏. 𝟏𝟎 = 𝟏 − 0.8643 = 𝟎. 𝟏𝟑𝟓𝟕
 t- Distribution
Theorem :
ഥ and S𝟐 are the mean and variance, respectively, of a random sample of size n
If 𝑿
taken from a population that is normally distributed with mean 𝝁 and unknown
ഥ −𝝁
𝑿
variance σ2. Then the random variable 𝑻 = 𝑺 has a t-distribution with
𝒏

𝝂 = 𝒏 − 𝟏 degrees of freedom (𝒅𝒇).

 t- Distribution
➢ Properties of t Distributions:
Let 𝒕𝝂 denote the 𝒕 distribution with 𝝂 𝑑𝑓.
1. Each 𝒕𝝂 curve is bell-shaped, centered at 0 and the total area under a t-curve
equals 1.
2. As 𝝂 increases, the spread of the corresponding 𝒕𝝂 curve decreases.
3. As 𝝂 → ∞ the sequence of 𝒕𝝂 curves approaches the standard normal curve
(so the 𝒛 curve is often called the t curve with 𝑑𝑓 = ∞).
 t- Distribution

Notation:

➢ Let 𝒕𝜶,𝝂 = the number on the measurement axis for which the area under
the t curve with 𝝂 𝒅𝒇 to the right of is 𝒕.

➢ For example 𝒕𝟎.𝟎𝟓,𝟏𝟎 is the 𝒕 critical value that captures an upper-tail area of
𝟎. 𝟎𝟓 under the t curve with 10 𝒅𝒇 , then 𝒕𝟎.𝟎𝟓,𝟏𝟎 = 1.812
Chi-Square Distribution
Theorem:
If 𝑆 2 is the variance of a random sample of size n taken from a normal
population having the variance 𝜎 2 , then the statistic

𝑛 − 1 𝑠 2
𝜒2 =
𝜎2

has a chi-squared distribution with 𝑣 = 𝑛 − 1 degrees of freedom.

Chi-Square Distribution
➢ The chi-square (𝜒 2 ) distribution is one of the most important continuous
probability distributions with many uses in statistical theory and inference.

➢ 𝜒α2 represent the 𝜒 2 value which we find an area of α. That is,

𝑃 𝜒 2 ≥ 𝜒α2 = α
Chi-Square Distribution

Properties of chi-square Distributions:

1. The total area under a 𝜒 2 -curve equals 1.
2. A 𝜒 2 -curve starts at 0 on the horizontal axis and extends indefinitely
to the right, approaching, but never touching, the horizontal axis as
it does so.
3. A 𝜒 2 -curve is right skewed.
4. As the number of degrees of freedom becomes larger, 𝜒 2 - curves
look increasingly like normal curves
Chi-Square Distribution
Chi-Square Distribution
Example:
Find the 𝜒 2 value with 7 degrees of freedom, leaving an area of 0.05 to the
right.

Solution:
𝝌𝟐0.05 = 14.067
F- Distribution
Theorem:
Let 𝑈 and 𝑉 be two independent random variables having chi-squared
distributions with 𝑣1 and 𝑣2 degrees of freedom, respectively. Then the
𝑈/𝑣1
distribution of the random variable 𝐹 =
𝑉/𝑣2

is known as the F-distribution with 𝑣1 and 𝑣2 degrees of freedom

F- Distribution

Properties of F Distributions:
1. The total area under a 𝐹-curve equals 1.
2. A 𝐹-curve starts at 0 on the horizontal axis and extends indefinitely
to the right, approaching, but never touching, the horizontal axis as
it does so.
3. A 𝐹-curve is right skewed.
F- Distribution
F- Distribution
Example:
Find the 𝐹 value with 6 and 10 degrees of freedom, leaving an area of 0.05 to
the right.
Solution:
𝑭𝟎.𝟎𝟓 = 3.217
Thank You