TYPES OF SAMPLING

DESIGNS/ METHODS
OF SAMPLING
REPORTER: ANGELLIE A. CAPUA
TYPES OF SAMPLING DESIGNS/
METHODS OF SAMPLING
A.
PROBABILIT
Y SAMPLING B.
NON-PROBABILITY
Sampling
TYPES OF PROBABILITY
SAMPLING
2.
1. RANDOM 3. STRATIFIED
SYSTEMATIC
SAMPLING SAMPLING
SAMPLING

4. MULTIPLE 5. MULTI
6. CLUSTER
SAMPLING OR STAGE
SAMPLING
DOUBLE SAMPLING
SAMPLING
. STRATIFIED SAMPLING
A method in which the researcher divides
the population into smaller groups that
don’t overlap but represent the entire
population. While sampling, these groups
can be organized and then draw a sample
from each group separately.
A business research team has to survey 120,000
employees working in different U.S. locations of a
company. The number of employees employed in
Calculation of the sample size for the Washington
various branches of the company is as follows:
office:
Number of Samples = (12,000/120,000) *20,000
Branch Office Number of Employees
Washington 20,000
New York 26,000 Sample Size of Washington Office = 2,000
New Jersey 19,000
California 38,000 Similarly, we can find the sample size for all branch
Kansas 17,000 offices using the above formula.
Total 120,000
If the total sample size is 12,000, the team can Branch Office Sample Size
determine the samples from each stratum or sub- Washington 2,000
group using the following formula. New York 2,600
New Jersey 1,900
Stratified Sampling = Total Sample Size / Entire California 3,800
Population * Population of Subgroups Kansas 1,700
Total 12,000
 STRATIFIED
SAMPLING
DISPROPORTIONATE PROPORTIONATE
OPTIMUM
ALLOCATION
A stratified sampling It refers to the selection from It refers to selecting units
method where the sample each sampling unit of a from each stratum. Each
population is not sample that is proportionate to stratum should be in
proportional to the the size of the unit. proportion to the
distribution within the Advantages of this procedure corresponding stratum the
population of interest. The includes representativeness population. Thus sample
implication is that the with respect to variables used obtained is known as
members of different as the basis of classifying optimum allocation sample.
categories and increased
subgroups do not have an
chances of being able to make
equal opportunity to be a comparisons between strata.
part of the research sample.
 PROPORTIONATE STRATIFIED SAMPLING
EXAMPLE
Suppose the population of a town If the sample size is 2000, we can determine the
has to be divided into three number of samples taken from each group using
categories based on their age. proportionate sampling.

Category Age Limit Population Proportion of sample size to population =

A Below 18 years 4100 2000/10000*1000 = 20%
Category Population Sample
B 18 – 44 years 3500
A 4100 20% of 4100 = 820
C 44 years above 2400

Total   10000 B 3500 20% of 3500 = 700

C 2400 20% of 2400 = 480

Total 10000 20% of 10000 = 2000

DISPROPORTIONATE STRATIFIED
SAMPLING EXAMPLE
Going by the above example, suppose the sample size remains
2000 people. Then, using the disproportionate method, the
researcher selects 600 people from category A and C and 800
people from category B.
Category Population Sample

A 4100 600

B 3500 800

C 2400 600

Total 10000 2000

 STRATIFIED
MERIT
SAMPLING
S
 It is a good representative of
the population.
 It is an improvement over the
earlier technique of sampling.
 It is an objective method of
sampling.
 Observations can be used for
inferential purpose.
DEMERI
TS
 Serious disadvantage of this method is that it
is difficult for the researcher to decide the
relevant criterion for stratification.
 Only one criterion can be used for
stratification, but generally it seems more
than one criterion relevant for stratification.
 It is costly and time consuming method.
 Selected samples may be representative with
reference to the used criterion but not for the
other.
 There is a risk of generalization.
4. MULTIPLE OR DOUBLE
REPETITIVE SAMPLING
This is most frequently used for establishing the
reliability of a sample. When employing a mailed
questionnaire, double sampling is sometimes used
to obtain a more representative sample. This is
done because some randomly selected subjects
who are sent questionnaires may not return them.
4. MULTIPLE OR DOUBLE
REPETITIVE SAMPLING
(CONTINUATION)
Obviously, the missing data will bias the result of the study,
if the people who fail to reply the query differ in some
fundamental way from the others. To eliminate this bias, a
selected sample may be drawn at random from the non-
respondents and the people interviewed to obtain the
desired information. Thus this technique is also known as
repeated or multiple sampling.
 MULTIPLE OR DOUBLE REPETITIVE
SAMPLING
MERIT
 Thus samplingS
procedure leads to
the inferences of free determine
precision based on a number of
observations.
 This technique of sampling
reduces the error.
 This method maintains the
procedure of the finding evaluate
the reliability of the sample.
DEMERI
TSof sampling
 This technique
cannot be used for a large
sample . It is applicable only
for small sample.
 This technique is time
consuming and costly.
 Its planning and
administration is more
complicated.
 MULTI STAGE
This sample is SAMPLING
more comprehensive and representative
of the population. In this type of sampling primary
sample units are inclusive groups and secondary units
are sub-groups within these ultimate units to be
selected which belong to one and only one group. The
individuals are selected from different stages for
constituting the multistage sampling.
Your research objective is to evaluate online spending patterns of households in the
CALABARZON through online questionnaires. You can form your sample group
comprising 200 households in the following manner:
1. Choose 5 cities/municipalities in CALABARZON using simple random sampling (or
any other probability sampling).
2. Choose 2 barangays from each chosen city/municipality using simple random or
systematic sampling methods.
3. Choose 20 households from each barangay using simple random or systematic
sampling methods. 
4. This will result in 200 households to be included in your sample group.
 MULTI STAGE
SAMPLING
MERIT DEMERI
S
 It is a good representative of the TS
 It is a difficult and complex
population. method of sampling.
 Multistage sampling is an  It involves errors when we
improvement over the earlier consider the primary stages.
methods.
 It is again a subjective
 It is an objective procedure of
sampling. technique of sampling.
 The observations from multi stage
sample may be used for inferential
purpose.
 CLUSTER
To select SAMPLING
the intact group as a whole is
known as a cluster sampling. In cluster
sampling the sample units contain groups
of element (cluster) instead of individual
members or items in the population.
 CLUSTER SAMPLING
MERIT DEMERI
S representative of
 It may be a good TS is not
Cluster sampling
the population.
free from errors.
 It is an easy method.
 It is an economical method.
It is not comprehensive.
 It is practicable and highly
applicable in education.
 Observations can be used for
inferential purpose.
 NON-
PROBABILITY
SAMPLING
 NON-PROBABILITY
A sampling SAMPLING
technique in which the researcher
selects samples based on his/her subjective
judgment rather than random selection. It is a
less stringent method in which not all members
of the population have an equal chance of
participating in the study. This sampling method
depends heavily on the expertise of the
researchers.
 TYPES OF NON-
PROBABILITY SAMPLING
1. INCIDENTAL/ 2. JUDGMENT
ACCIDENTAL SAMPLING SAMPLING

3. PURPOSIVE 4. QUOTA
SAMPLING SAMPLING

5. SNOWBALL 6. PURPOSIVE/EXPERT
SAMPLING CHOICE SAMPLING
 INCIDENTAL OR
ACCIDENTAL Sampling
A sampling technique where samples are selected from
the population only because they are conveniently
available to the researcher. Researchers choose these
samples just because they are easy to recruit, or
because the researcher is unable to employ more
acceptable sampling methods.
INCIDENTAL OR ACCIDENTAL Sampling
MERIT DEMERI
S method of
 It is very easy TS
It is not representative of
sampling. the population.
 It is frequently used method It is not free from errors.
in behavioral sciences.
Parametric statistics
 It reduces the time, money cannot be used.
and energy i.e. it is an
economical method.