Professional Documents
Culture Documents
Statistics Lecture Part 2
Statistics Lecture Part 2
TO RESEARCH
“How many participants
should be chosen for a
survey”?
Sample Size Determination
1. Level of Precision
2. Confidence Interval
3. Degree of Variability
Criteria Need to be Specified to
Determine the Appropriate Sample Size
Level of Precision
Also called sampling error, the level of
precision, is the range in which the true
value of the population is estimated to
be.
Criteria Needed to be Specified to
Determine the Appropriate Sample Size
Confidence Interval
It is a statistical measure of the number of
times out of 100 that results can be expected
to be within a specified range.
Criteria Need to be Specified to
Determine the Appropriate Sample Size
Degree of Variability
Depending upon the target population
and attributes under consideration, the
degree of variability varies considerably.
Methods in Determining the
Sample Size
Estimating the Mean or Average
The sample size required to estimate the
population mean µ to with a level of confidence
with specified margin of error e, given by
( e )
2
Zσ
n≥
Where:
Z is the z-score corresponding to level of confidence
e is the level of precision.
Reminders:
If When σ is unknown, it is common practice
to conduct a preliminary survey to determine
s and use it as an estimate of σ or use results
from previous studies to obtain an estimate of
σ. When using this approach, the size of the
sample should be at least 30. The formula for
the sample standard deviation s is
2
∑ (x − x̄)
s=
n−1
Example:
A soft drink machine is regulated so
that the amount of drink dispensed is
approximately normally distributed
with a standard deviation equal to 0.5
ounce. Determine the sample size
needed if we wish to be 95% confident
that our sample mean will be within +.
03 ounce from the true mean.
Solution:
A soft drink machine is regulated so that the amount of
drink dispensed is approximately normally distributed with
a standard deviation equal to 0.5 ounce. Determine the
sample size needed if we wish to be 95% confident that our
sample mean will be within +.03 ounce from the true mean.
( 0.03 )
2
1.96(0.5)
n≥ = 10,671.11
(e)
2
Z
n≥ p(1 − p)
Where:
Z is the z-score corresponding to level of confidence
e is the level of precision.
P is population proportion
Example:
Suppose we are doing a study on the
inhabitants of a large town, and want to find
out how many households serve breakfast in
the mornings. We don’t have much
information on the subject to begin with, so
we’re going to assume that half of the
families serve breakfast: this gives us
maximum variability. So p = 0.5. We want
99% confidence and at least 1% precision.
Solution:
Suppose we are doing a study on the inhabitants of a large
town, and want to find out how many households serve
breakfast in the mornings. We don’t have much information on
the subject to begin with, so we’re going to assume that half of
the families serve breakfast: this gives us maximum variability.
So p = 0.5. We want 99% confidence and at least 1% precision.
The z – score for confidence level 99% in the z – table is 2.58.
( 0.01 )
2
2.58
n≥ 0.5(1 − 0.5) = 16,641
We need a 16,641 sample for our study.
Methods in Determining the
Sample Size
Slovin’s Formula (Simplified form of Proportions for
finite population)
1000
n≥ = 285.71
1 + 1000(0.05) 2
4 (e)
2
1 Z
n= ≈ 385
Where:
Confidence level is 95%
The level of precision is 0.05
Finite Population Correction
If the population is small then the sample size
can be reduced slightly.
n0
n=
no − 1
1+
N
Where:
no is Cochran’s sample size recommendation
N is the population size
Exercises:
Determine the sample size of the following
problems.
1. A dermatologist wishes to estimate the
proportion of young adults who apply
sunscreen regularly before going out in
the sun in the summer. Find the minimum
sample size required to estimate the
proportion with precision of 3%, and 90%
confidence.
Exercises:
Determine the sample size of the following
problems.
2.The administration at a college wishes
to estimate, the proportion of all its
entering freshmen who graduate within
four years, with 95% confidence.
Estimate the minimum size sample
required. Assume that the population
standard deviation is σ = 1.3 and precision
level is 0.05.
SAMPLING DESIGN: Basic
Concepts and Procedure
1. Probability Sample
2. Non - Probability Sample
Probability Samples
500
k= = 10
50
We start to get a sample starting form i and
for every kth unit subsequently. Suppose the
random number i is 5, then we select 5, 15, 5,
35, .. .
Stratified Random Sampling
(N) ( 500 )
n 50
n1 = N1 = 200 = 20
(N) ( 500 )
n 50
n2 = N2 = 300 = 30
The sample sizes are 20 from A and 30 from B. Then the units
from each institution are to be selected by simple random
sampling.
Cluster Sampling
• It is a way to randomly select
participants from a list that is too large
for simple random sampling.
• The clusters are constructed such that
the sampling units are heterogeneous
within the cluster and homogeneous
among the clusters.
Cluster Sampling
Obtaining a Cluster Sample
1. Divide the population into non-overlapping
clusters.
2. Number the clusters in the population from 1 to N.
3. Select n distinct numbers from 1 to N using a
randomization mechanism. The selected clusters are
the clusters associated with the selected numbers.
4. The sample will consist of all the elements in the
selected clusters.
Example:
1. Non-responses
2. Interviewer Error
3. Misrepresented Answers
4. Data entry errors
Sources of Non-Sampling Error
5. Questionnaire Design
6. Wording of Questions
7. The order of the questions, words, and
responses