Scribd
Upload
3 views

Sampling Distribution

The document discusses sampling distribution and its properties. Sampling distribution is the distribution of sample statistics like means from repeated samples. It approaches a normal distribution as sample size increases due to the central limit theorem. The standard error specifies how well a sample mean estimates the population mean and decreases with larger samples.

Uploaded by

johnyuhanna
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
3 views

Sampling Distribution

The document discusses sampling distribution and its properties. Sampling distribution is the distribution of sample statistics like means from repeated samples. It approaches a normal distribution as sample size increases due to the central limit theorem. The standard error specifies how well a sample mean estimates the population mean and decreases with larger samples.

Uploaded by

johnyuhanna
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

Sampling

Distribution
Ibrahim Altubasi, PT, PhD
The University of Jordan
Sample Distribution vs.
Sampling Distribution
Sample is a subset of population. Each sample contains a finite (countable)
number of scores, the number of scores represented by the letter n, and the
scores in a sample has a distribution. This is sample distribution.

33 36 38 37 33 38 36 35 34 37 40 38 36 35 31 37 36 33
33 30 35 37 39 32 39 32 37 35 36 39 33 40 37 34 34 37
Sampling distribution
Sample 1 (n=30) Sample 2 (n=30)
x̅ = 51, s = 4.5 x̅ = 50 , s= 5.2

Population
(μ=50, σ=5)
Sample … Sample 3 (n=30)
(n=30) x̅ = 48, s= 4.6

Sample 5 (n=30) Sample 4 (n=30)


x̅ = 60, s =5 x̅ = 49, s= 5.1
Sampling Distribution
• Each sample will have its statistics, such as mean, SD, median etc. Usually,
the sample statistic will be different from population parameter and the
discrepancy is sampling error.

• Two samples (with equal sample size) from the same population usually
will be different.

• Sample statistics are variables. A sample statistic (e.g. sample mean) from
repeated samples will have a distribution. The distribution of sample
statistic is called sampling distribution. Each sample statistic will have a
corresponding sampling distribution.

• A sampling distribution is a distribution of statistics obtained by selecting


all the possible samples of a specific size from a population.

• Sampling distribution is a distribution of statistics (as opposed to a


distribution of scores). The sampling distribution of means is an example
of a sampling distribution.
Sampling Distribution
The process of constructing the sampling distribution of sample
means. A sample of size n is selected, then the sample mean is
computed and placed in a frequency distribution. This process is
repeated over and over until all the possible random samples are
obtained and the complete set of sample means is in the
distribution.
Sampling Distribution
Properties of the sampling distribution of means

Shape of the distribution: if the population from which the


samples are selected is a normal distribution, then the sampling
distribution of the means is normal.

Mean of the distribution: The mean of the sample means (μx̅ )is
equal to population mean μ.

Standard deviation of the distribution: The SD of the distribution


of sample means is called the standard error of the mean (SE),
which is denoted as σx̅ = σ/√n
Sampling Distribution
The Central Limit Theorem (CLT)

For any population with mean μ and variance σ² (with any shape), the
sampling distribution of sample means will approach a normal distribution
as n approaches infinity. The larger n is, the better the approximation is.

Rule of thumb: the shape of the sampling distribution of means approximates


normal when n=30.
Sampling Distribution
When the population distribution is non-normal, the sampling distribution of
means is approximately normal when sample size n is relatively large (n>30),
with mean μx̅ = μ and standard error Sampling Distribution σx̅ = σ/√n

When we use the sample mean as an estimate of the population mean, we do


not expect the sample mean to be exactly the same as population mean;
however, it should provide a good estimate. The SE specifies precisely how
well a sample mean estimates its population mean – that is, how much error
you should expect, on average, between x̅ and μ.

Notice that σx̅ = σ/√n, this tells that as the sample size increases, the error
between the sample mean and the population mean should decrease. Thus a
large sample should be more accurate than a small sample. This rule is known
as the Law of large numbers.
Sampling Distribution
The use of sampling distribution:
Q: The population of scores on SAT forms a normal distribution with μ=500
and σ= 100. If you take a random sample of n=25 students, what is the
probability that the sample mean will be greater than 540?
Step 1: find the properties of the
distribution of sample means with n=25

The shape of this sampling distribution:


normal? because…
The mean of the sampling distribution:
μx =500
The standard error of this sampling
distribution:
σx = 100/√25 = 20

Step 2: Zx̅ = X̅ -μx̅ = 540- 500 =2


σx̅ 20

p(z≥2) = .023
Sampling Distribution
Q: The population of scores forms a positively skewed distribution with μ=70
and σ= 48. If you take a random sample of n=64 students, what is the
probability that the sample mean will be between 60 and 80?

Step 1: find the properties of the distribution of sample means with n=64

The shape of this sampling distribution: normal? Because the sample size is 64.

The mean of the sampling distribution: μx̅ = 70

The standard error of this sampling distribution: σx̅ = 48/√64 = 6

Step 2:
Zx̅ -60 = X̅ -μx̅ = 60 -70 = -1.67
σx̅ 6

Zx̅ -80 = 80 -70 = 1.67


6
p(-1.67 ≤ z ≤ 1.67) = .905
Sampling Distribution
Q: The average age for registered votes in the county is μ =39.7 years old with σ
=11.8. Assume the distribution of age is normal. During a recent jury trial in
the county courthouse, a statistician noted that the average age of the 12 jurors
was 50.4 years old. How likely is it to obtain a jury this old or older by chance?

Step 1: find the properties of the distribution of sample means with n=12
The shape of this sampling distribution: normal? Because the population
distribution is normal.
The mean of the sampling distribution: μx̅ = 39.7

The standard error of this sampling distribution: σx̅ = σ/√n= 11.8/√12 = 3.406

Step 2: Is it reasonable to conclude that


Zx̅ -54.4 = X̅ -μx̅ = 50.4 – 39.7= 3.141 this jury is a random sample of
σx̅ 3.406 registered voters? No, because
the chance of getting a sample as
p(z ≥ 3.141) = .0008 old from the population
of registered voters is very small

You might also like