TYPES OF SAMPLING :

PROBABILITY & NON-

PROBABILITY
DR. RASHMI GORE
OBJECTIVES OF LECTURE

After this lecture you will be able to:

• Define the term population & Sample.
• Explain the steps involved in the process of sampling.
• Describe methods of sampling : Probability sampling & Non-probability sampling.
• Explain the advantages and limitations of various types of probability sampling.
• Describe the advantages and limitations of various types of Non-probability sampling.
CONCEPT POPULATION & SAMPLE

POPULATION SAMPLE
• A population is any group of individuals • In research, term sample is a group
that have one or more characteristics in of people, objects, or items that
common and that are in interest of are taken from a larger population
researcher. (Best & Kahn,1995) for measurement. The sample
• A population refers to any collection of should be representative of the
specified group of human beings or of population to ensure that we can
non human entities such as objects, generalize the findings from the
educational institutions, time units, research sample to the population as
geographical areas, prices of a whole.
commodities, salary of an individual etc.
( L. Kaul,2010)
STEPS OF SAMPLING PROCESS

• Defining the population.

• Preparing sampling frame,
• Selecting a representative sample through proper sampling method.
• Obtaining an adequate sample.
(The adequacy of sample is depended upon
1. Our knowledge about population.
2. The method used in drawing the sample.)
METHODS OF SAMPLING

There are two broad categories of sampling-

• Probability sampling or random sampling.
• Non- Probability sampling or non-random sampling.
PROBABILITY SAMPLING

• In probability sampling, a sample has been selected in such a

way that every element chosen has a known probability
of being included.
• Probability sampling means that every member of the target
population has a known chance of being included in the sample.
CHARACTERISTICS OF PROBABILITY SAMPLING

• Generally used in Fundamental Researches : main objective is

to generalize the result
• based on statistical concepts:
• Larger sample more precision value of parameter
• Normal distribution
• Best for homogeneous population
TYPES OF PROBABILITY SAMPLING

There are four types of probability sampling :

• Simple random sampling
• Systematic random sampling
• Stratified random sampling
• Cluster random sampling
SIMPLE RANDOM SAMPLING

• In simple random sampling, each member of the population(N)

has an equal chance of being selected in the sample (n) by
randomization.
• This method is also called an equal probability of selection method.
Techniques of randomization
• Lottery method
• Use of table of random numbers
SIMPLE RANDOM SAMPLING: LOTTERY METHOD

Procedure:
• Define population
• Prepare sampling frame
• Arrange the no. of units without order
• Mix the slips or chits after naming or labelling every unit of the population
• Draw require no. of units from those well mixed chits
SIMPLE RANDOM SAMPLING: LOTTERY METHOD
EXAMPLE

• The example in which the assignment of 25 students

out of 250 are chosen is an example of the lottery
method at school. Each of the 250 students would be
assigned a number between 1 and 250, after which 25 of
those numbers would be chosen at random.
SIMPLE RANDOM SAMPLING: LOTTERY METHOD WITH
REPLACEMENT & WITHOUT REPLACEMENT TECHNIQUES

SAMPLING WITH REPLACEMENT SAMPLING WITHOUT REPLACEMENT

• The technique of sampling is said to • whereas sampling without

be with replacement when a replacement, the units once drawn
sampling unit is drawn from a finite and selected as sample, not be
population and after its returned to that population.
characteristic(s) have been recorded, In order to account for this difference
is returned to that population, before when using the table or generate for
the next unit is drawn random digits, one must ignore the
repeated number that was included in
the labeling.
ADVANTAGES & LIMITATIONS OF LOTTERY
METHOD
• Advantages –
• Equal chance of every unit of population to be selected in sample.
• Best for homogeneous population.
• Limitations –
• Not possible in a larger/infinite populations.
• Impossible to include specific units of population.
SIMPLE RANDOM SAMPLING: USE OF TABLE OF
RANDOM NUMBERS

• For large population simple random method may be used

through using computer generated random number
programme or random digit table prepared by Kendall & Smith,
Tippet, Fisher & Yates etc.
• Save time, money, labour.
• No special technical assistance is needed.
LIMITATIONS OF USING TABLES OF RANDOM
NUMBERS

• Can not provide true representative sample in heterogeneous

population.
• When the population is infinite, difficult to prepare sample
frame.
• Inclusion of specific units of population is not possible.
SYSTEMATIC RANDOM SAMPLING

When -
• population is finite & can be accurately listed or availability of sampling
frame.
• Units of population are alphabetically /merit wise/ etc. arranged in a
systematic manner.
Systematic sampling, after numbering N units in population from
1 to N is to select a sample of n units by taking a unit at random
from the first k unit and every kth thereafter.
SYSTEMATIC RANDOM SAMPLING

• Systematic sampling is a type of probability sampling method in which

sample members from a larger population are selected according to a
random starting point but with a fixed, periodic interval. This interval, called
the sampling interval, is calculated by dividing the population size by the desired
sample size. - [Link]
• When population is finite & can be accurately listed or availability of sampling
frame.
SYSTEMATIC RANDOM SAMPLING: STEPS

1. Define population.
2. Number the units of population from 1 to N.
3. Decide sample size (n).
4. Decide the sampling interval (k) = population size / sample size.
5. Choosing starting point by randomly selecting one number between 1 and k.
6. After determination of k and starting point the rest units of the sample can be
selected If you have a starting point of 15 and a sample interval of 100, the first
member of the sample would be 115, and so forth.
SYSTEMATIC RANDOM SAMPLING: EXAMPLE

• when a principal wants to select 6 teachers out of 60 of their

staff for a particular task. He will select after preparing list of
all appointed teachers in alphabetical manner and randomly
select one, suppose no. 5 is selected randomly. Then he will
select 15th , 25th , 35th 45th & 55th.
SYSTEMATIC RANDOM SAMPLING: LIMITATIONS

• Advantages –
• Simplicity
• Practicality
• Speediness
• Limitations –
• Randomly selected first element has influence on the selection of
other element.
• Not for heterogeneous & infinite population.
STRATIFIED RANDOM SAMPLING

• When units in a sample are proportional to its population, the sample is called
stratified.
• In stratified sampling researcher has to divide the population of N units into sub-
populations which is called strata like N1, N2, N3,……… Nn, respectively.
• The sample sizes within the strata are denoted by n1, n2, n3……. nn respectively.
• The usual stratification factors are gender, age, socio-economic status, educational
background, residence (rural/urban), occupation, religion, caste, general intelligence etc.
STRATIFIED RANDOM SAMPLING: STEPS

• Defining the population.

• Deciding the criteria on which population will be formed like male/
female/transgender, higher/middle/lower SES, rural/urban/semi urban etc.
• Dividing the population into stratum on the basis of stratification variables.
• Listing the units in each stratum.
• Selecting required no. of units from each strata by using appropriate random
selection techniques.
STRATIFIED RANDOM SAMPLING: CLASSIFICATION

There are two types of stratified random sampling :

• Proportionate stratified random sampling
Selection of a sample from each sampling unit is in proportion to its size and unit.
• Disproportionate stratified random sampling
The selection in which each unit is not proportionate to the size of the units in population
but depends upon researcher’s judgement and convenience.
EXAMPLE OF PROPORTIONATE & DISPROPORTIONATE
STRATIFIED RANDOM SAMPLING

Distribution of students according to their programmes

Students enrolled in Population Proportionate Disproportionate
programmes Stratified Sampling Stratified Sampling

B.A. 200 20 25
[Link]. 100 10 25
[Link]. 400 40 25
B.B.A. 300 30 25
Total Np=1000 n=100 n=100
STRATIFIED RANDOM SAMPLING: ADVANTAGES &
LIMITATIONS
Advantages –
• when list of units or individuals in population are not available.
• This method is also suitable when cent- percent response is difficult to secure in desired
time.
• Stratified random sampling provides more accurate results than simple random sampling if
stratifications results are homogeneous within strata.
Limitations –
• Can’t use stratified sampling method when population is heterogeneous in nature
internally in sub-groups.
• Researchers can't confidently classify every member of the population into a
subgroup.
CLUSTER SAMPLING METHOD

• Cluster sampling is a method of probability sampling that is

often used to study large populations, particularly those that
are widely geographically dispersed. Researchers usually use
pre-existing units such as schools or cities as their clusters.
• In case of infinite population or not reliable list of
elements and geographically scattered population, cluster
sampling method is used.
CLUSTER SAMPLING OR AREA SAMPLING

• The nature of strata internally is homogeneous in stratified

random sampling but in cluster sampling method, its
nature is heterogeneous.
• In cluster sampling, cluster is selected randomly i.e. a collective
type of units like schools, cities etc. not single elements i.e.
individual student, teacher etc.
CLUSTER SAMPLING: EXAMPLE

• If a researcher is interested in the average reading level of all the seventh-graders in his
state.
• It would be very difficult to obtain a list of all seventh-graders and collect data from a
random sample spread across the state. However, he can easily obtain a list of all schools
and collect data from a subset of these, thus he decides to use the cluster sampling
method.
• To survey the health status of primary school children of a state, researcher selects
randomly clusters of units under cluster sampling method.
CLUSTER SAMPLING: ADVANTAGES

• Time- and cost-efficient especially for samples that are widely

geographically spread and would be difficult to properly sample
through other method.
• High external validity, because cluster sampling uses
randomization, if the population is clustered properly, sample
will reflect the characteristics of the larger population.
CLUSTER SAMPLING: LIMITATIONS

• In comparison to simple random sampling internal validity is

less strong.
• Cluster sampling is much more complex to plan than other
forms of sampling.
NON - PROBABILITY SAMPLING TECHNIQUES

• When the units of the population are selected at the discretion of the
researcher
• Non-probability sampling is a method of selecting units from a
population using a subjective (i.e. non-random) method. Since
non-probability sampling does not require a complete survey frame,
it is a fast, easy and inexpensive way of obtaining data.
• Non-probability sampling is defined as a sampling technique in
which the researcher selects samples based on the subjective
judgment of the researcher rather than random selection
NON - PROBABILITY SAMPLING TECHNIQUES:
TYPES

• Incidental, accidental or convenient sampling

• Purposive or judgemental sampling
• Quota sampling
• Snow ball or chain sampling
• Dense sampling
• Double sampling
INCIDENTAL, ACCIDENTAL OR CONVENIENT SAMPLING

• Accidental or incidental is that type of sampling in which a researcher pick up

data or information's from those who fall into hand or present at the time of
research. It continues the process till the completion of the sample size.
• For instance, a person who is obtaining opinions for a political poll at a
shopping mall by randomly selecting passers-by is using a form of accidental
sampling
• Convenience sampling (also called accidental sampling or grab sampling) is a
method of non-probability sampling where researchers will choose their
sample based solely on the convenience.
WHEN IT IS USED ?

• When researchers are more concerned with the number of responses, and not the
actual representativeness of the sample.
• When budgeting is tight and researchers want a low-cost method to collect data.
• When pilot testing.
• When observing habits, opinions, and viewpoints of a target audience.
• When collecting feedback on various brands or organizations.
• When researchers don’t have access to the full target population for a
representative sample.
ADVANTAGES & LIMITATIONS

Advantages
• Time & cost effective
• Uncomplicated method of data collection
Limitations
• Biasedness of researcher
• Low external validity
PURPOSIVE OR JUDGEMENTAL SAMPLING

• Purposive sampling refers to a group of non-probability sampling

techniques in which units are selected because they have
characteristics that researcher needs in his sample. In other words,
units are selected “on purpose” in purposive sampling.
• The selection of sample depends upon the judgement of researcher
on the basis of past experiences.
• Purposive sampling is common in qualitative research and mixed
method research. It is particularly useful if a researcher needs to find
information-rich cases or make the most out of limited resources.
PURPOSIVE OR JUDGEMENTAL SAMPLING

• Researcher uses his judgement and decides that which portion of the
population will sufficiently serve the purpose of his problem and leaves
other portion of the population.
• Researcher selects the units of population which/who provides richest
information and which are of most interest of researcher.
• Example: If a researcher wants to study the feeling of learners when
they are learning through online courses he can take judgement to
select registered learners from SWAYAM platform.
LIMITATIONS

• prone to bias.
• The findings of studies based on either convenience or purposive sampling can only
be generalized to the (sub)population from which the sample is drawn, and not to the
entire population.
QUOTA SAMPLING

• Quota sampling method is similar to stratified random

sampling. But it is non-randomly sample unit selection within
each strata.
• First researcher has to identify the groups and sub-groups of
interest, then determine the number of people to be Included
in each strata and finally select the sample of each group.
QUOTA SAMPLING: EXAMPLE

• If a population of 1000 students comprises of 700 boys

and 300 girls then if we want to apply Quota sampling
technique, in the sample of 100, the 70 boys and 30 girls
will be selected according to researchers convenience not
randomly.
SNOW BALL OR CHAIN SAMPLING

• In this method participant who are voluntarily selected are asked to

explore other people with the same characteristics and may be willing to
participate in the study. Thus sample becomes larger and larger. It is
viewed as snowball is rolling down a hill, and getting bigger and bigger in
size.
• It is used when sampling frame is not available and it is difficult to locate
the members for inclusion in the sample.
• Good for hidden population which is not easily identifiable.
SNOW BALL OR CHAIN SAMPLING: EXAMPLE

• To study of behaviour of students who are drug addicted.

• Difficulties faced by female administrator in their workplace.
• Socio-economic behaviour of ragged students etc.
DENSE SAMPLING

• When the researcher select 50% or more from the population and
takes a majority of individuals having specified traits or
characteristic which are of interest to him, it is called dense
sampling.
• Example: When a researcher wants to study the job satisfaction
among private doctors in a city, suppose total no. of private doctors
in that city are [Link] he selects 50 % or 500 who are continuously
serving since 10 years, it will be the example of dense sampling.
DOUBLE SAMPLING

• Double sampling is a two-phase method of sampling for an

experiment, research project, or inspection. An initial
sampling run is followed by preliminary analysis, after
which another sample is taken and more analysis is run.
CONSIDERATIONS WHILE SELECTING A SAMPLE

• Objectives of the study – ( for generalizing the results for

whole population or providing the immediate solution of the
problem)
• Type of study – (survey or experimental or qualitative)
• Recourses available – (time, cost, manpower, technical
assistance)
THANKS