Basic Concepts in Samples and

Sampling
• Population: the entire group under study as defined by
research objectives. Sometimes called the
“universe.”
• Researchers define populations in specific terms such
as heads of households, individual person types,
Student population, Plants in field, families, types of
retail outlets, etc.
• Target Population: is total population about which
one requires information
• Sampled Population: is more accessible population out
of target population . Which is available at the time of enquiry
Basic Concepts in Samples and Sampling

Sample: a subset of the population that should represent the

entire group
Sampling units: The population is divided into parts before selecting
a sample. These parts are known as sampling units or units.
Sampling Frame:- Complete list of all the sampling units in a
population
Requirements of a reasonably good frame.
■ Not contain inaccurate sampling units
■ Be complete and exhaustive
■ Be free from errors of omission and duplication of sampling
units
■ Be as up-to-date as possible at the time of use
Sampling:-Sampling is a procedure by which we draw a part of
an aggregate in the belief that the part will possesses the same
qualities which that aggregate possesses.
Census: A census is a collection of data from all units in
the statistical population for a certain characteristics. Or
Census is a complete enumeration of the statistical
population.
Types of censuses
1.Population census
2.Agricultural census
3.Economic census
and other types of
census.
Advantages of Sampling
❖ Time Saving: To contact the whole population would be time consuming
❖ Reduced Cost: Data are secured from only a small fraction of the aggregate
and Expenditures are small
❖ Greater Speed: Data can be collected and summarized more quickly with a
sample than with a complete count
❖ Greater Scope: More scope and flexibility regarding the types of information
that can be obtained
❖ Greater Accuracy: Personnel of higher quality can be employed
and given intensive training & More careful supervision of the field
work and processing of results becomes feasible
❖ Destructive Nature of Some Tests: Sampling is essential to
obtaining the data when the measurement process physically damages or
destroys the sampling unit under investigation
❖ Adaptability: Many topics could be in a single sample survey.
covered
This may not be possible in census due to wider coverage we can notgo in
detail
 Parameter
• Numerical quantity describing a population
Population mean(μ), variance (σ2) proportion (P).
• Parameters are usually denoted by Greek letters
• Parameters are usually unknown
• Parameters are fixed (constant) values

Statistic
• Numerical quantity calculated from the sample
• Sample mean ( X ), variance(S2)
• Statistics are variables as it varies from sample to
sample
 Sampling With and Without Replacement
Sampling With Replacement:- Sampling is said to be with
replacement when we draw a sampling unit from a
population and return it to the population before next unit
is drawn. In this case sampling unit can be chosen more
than once. On the other hand ,

Sampling Without Replacement:- if we do not return the

sampling unit to the population and drawn the next unit,
the sampling is said to be without replacement. In this case
the sampling unit can be chosen only once.
 SAMPLING METHODS

Probability Sampling Nonprobability Sampling

Simple Convenience Snowball

Systematic Quota
random sampling sampling
sampling Cluster sampling
sampling sampling
Judgment
Stratified sampling
sampling

8
 Simple random sampling
• Each element of the population has a known and
equal probability of selection
• Every element is selected independently from
other elements
• The probability of selecting a given sample of n
elements is computable (known)
• Statistical inference is • Representative samples are
possible large and expensive
• It is easily understood • Standard errors are larger than
in other probabilistic sampling
techniques
• Sometimes it is difficult to
execute a really random sampling
 Systematic sampling
• A list of N elements in the population is compiled and
ordered according to a specified variable
• Unrelated to the target variable (similar to SRS)
• Related to the target variable (increased representativeness)
• A sampling size n is chosen
• A systematic step of k=N/n is set
• A random number s between 1 and N is extracted
and represents the first element to be included
• Then the other elements selected are s+k, s+2k,
s+3k…
• Cheaper and easier than SRS Less representative (biased) if
• More representative if order is the order is cyclical
related to the interest variable
(monotone)
• Sampling frame not always necessary
 Stratified sampling
• Population is partitioned in strata through control variables
(stratification variables), closely related with the target
variable, so that there is homogeneity within each stratum
and heterogeneity between strata
• A simple random sampling frame is applied in each
strata of the population
• Proportionate sampling – size of the sample from each stratum is
proportional to the relative size of the stratum in the total
population
• Disproportionate sampling: size is also proportional to the
standard deviation of the target variable in each stratum

❖ Gains in precision ❖ Stratification variables

❖ Include all relevant may not be easily
sub population even if identifiable
small ❖ Stratification
can be expensive
 Cluster sampling
• The population is partitioned into clusters
• Elements within the cluster should be as heterogeneous
as possible with respect to the variable of interests (e.g.
area sampling)
1. A random sample of clusters is extracted through SRS
(with probability proportional to the cluster size)
• 2a. All the elements of the cluster are selected (one-stage)
• 2b. A probabilistic sample is extracted from the cluster (two-
stage cluster sampling)

• Reduced costs • Less precision

• Higher • Inference can be
feasibility difficult
 Cluster sampling
Section 1 Section 2

Section 3

Section 5

Section 4
 SAMPLING METHODS
Nonprobability Sampling

Convenience Quota Snowball

sampling sampling sampling
Judgment
sampling
Convenience sampling
❖ The sampling procedure used to
obtain those units or people most
conveniently available
• Cheapest method • Selection bias
• Quickest method • Non representativeness
• Inference is not
possible
14
Judgment or purposive sample
In judgment sampling selection of units is carried out by a
subject matter expert who picks typical or
representative units i.e personal judgment rather than
chance alone determines which population elements are
selected as a sample
When it is not feasible or practicable to obtain a random
sample due to lack of time or money
Where randomness is not critical, as in a preliminary study
In case of small population expert judgment may be better
than
random methods in selecting representative sample

15
 Quota sampling
1. Define control categories (quotas) for the population
elements, such as sex, age…
2. Apply a restricted judgmental sampling so that
quotas in the sample are the same of those in the
population
• There is no guarantee that
• Cheapest method sample
the is representative
• Quickest method (relevance of control
characteristic chosen)
• Many sources of selection bias
• No assessment of sampling error
 Snowball sampling
• A first small sample is selected randomly
• Respondents are asked to identify others
who belong to the population of interests
• The referrals will have demographic and
psychographic characteristics similar to the
referrers
• Lower costs • Inference is not
• Low variability possible
• Useful for rare
populations
 Accuracy and precision
Accuracy: the degree to which the sample estimate is
close to the true population value – maximum
accuracy is obtained when the estimate equals the
true population value
Precision: the variability of the sample estimate in
repeated measurements (across different samples)
– maximum precision is obtained when the
estimate is the same across all samples
The standard error of an estimator is a measure of
precision
• Sampling distribution of Means
• (Sampling with replacement)
Question:-A population consists of 5 values, 2, 4, 6, 8 and 10.A
simple random sample of size 2 is to be selected with replacement.
1. Find Population Mean µ and Variance (σ2)
2. Draw all possible random samples of size 2 with replacement
and then
3. Construct the sampling distribution of sample means.
4.Verify the properties of sampling distribution of
means i.e ( a ) µ =
x

µ 2
(b ) 2
x =σ
σ n
 1. Population Results
X X2
2 4 Σ X = 30 , N =
4 16 5µ , Σ X =30 =
6 36 = N 5 6
8 64 ΣX 2 – ( ΣX
σ 2

10 100 = N

2 N
30 220 
σ 2 220 – (30
ΣX ΣX 2 52
=  5
 
σ 2
= 44 –36 =
8
20
2.
N=5 n=2
Method=with replacement
Total number of possible
samples.
K= (N)n=52=25
Possible samples Sample means Possible samples Sample means
K X K X
(2 , 2) 2 (6 , 8) 7
(2 , 4) 3 (6 , 10) 8
(2 , 6) 4 (8 , 2) 5
(2 , 8) 5 (8 , 4) 6
(2 , 10) 6 (8 , 6) 7
(4 , 2) 3 (8 , 8) 8
(4 , 4) 4 (8 , 10) 9
(4 , 6) 5 (10, 2 ) 6
(4 , 8) 6 (10 , 4) 7
(4 , 10) 7 (10, 6) 8
(6 , 2) 4 (10 , 8) 9
(6 , 4) 5 (10,10) 10
(6 , 6) 6
3. Sampling distribution of sample means:

Frequency Probability
X PX PX 2
f P

2 1 1/25 2/25 4/25

3 2 2/25 6/25 18/25
4 3 3/25 12/25 48/25
5 4 4/25 20/25 100/25
6 5 5/25 30/25 180/25
7 4 4/25 28/25 196/25
8 3 3/25 24/25 192/25
9 2 2/25 18/25 162/25
10 1 1/25 10/25 100/25
25 1 150/25 1000/25
Σf ΣP.X ΣP.X 2
4. From Sampling distribution of means:
•Mean: µ x =Σ P.X
= 150 / 25 = 6
•Variance 2
σ x= ΣP.X 2 –
[ΣP.X ]2
= 1000 – ( 150
25  25

=  

40 – 36 = 4
Verification of properties 8
(i)µx = µ (ii x =2 = =
2 σ
σ n 42
=6 )
• Sampling distribution of Means
• (Sampling without replacement)
Question:-A population consists of 5 values, 2, 4, 6, 8 and 10.A
simple random sample of size 2 is to be selected without
replacement.
1. Find Population Mean µ and Variance (σ2)
2. Draw all possible random samples of without
size 2 replacement and then
3. Construct the sampling distribution of sample means.
4. Verify the properties of sampling distribution of
means
i.e ( a ) µ x= µ 2
2 σ (N –
(b ) x = .
n n) ( N –
σ
1)
 1. Population Results
X X2
2 4 Σ X = 30 , N =
4 16 5µ , Σ X =30 =
6 36 = N 5 6
8 64 ΣX 2 – ( ΣX
σ 2

10 100 = N

2 N
30 220 
σ 2 220 – (30
ΣX ΣX 2 52
=  5
 
σ 2
= 44 –36 =
8
26
Possible samples Sample means( X )
(2 , 4) 3
(2 , 6) 4
(2 , 8) 5
(2 , 10) 6
(4 , 6) 5
(4 , 8) 6
(4 , 10) 7
(6 , 8) 7
(6 , 10) 8
(8 , 10) 9
3. Sampling distribution of sample means:

Frequency Probability
X
F P PX PX 2
3 1 1/10 3/10 9/10
4 1 1/10 4/10 16/10
5 2 2/10 10/10 50/10
6 2 2/10 12/10 72/10
7 2 2/10 14/10 98/10
8 1 1/10 8/10 64/10
9 1 1/10 9/10 81/10
10 1 60/10 390/10
Σf ΣP.X ΣP.X 2
4. From Sampling distribution of means:
•Mean: µ x =Σ P.X
= 60 / 10
•Variance
σ x== ΣP.X
2
6 2–
[ΣP.X]2
= 390 –( 60
10   10
= 


39 – 36 = 3
Verification of properties σ 2
(N – 8(3)
(i)µ = µ
x (ii σx
2
n)n(N –1)
= =
2(4) 3
=6 )=