SAMPLING TECHNIQUES
Dr.Bharath V MFM., M.Com., Ph.D
Assistant Professor
Kristu Jayanti College
Bengaluru
1
bharath.v@kristujayanti.com
Sampling Methods
• Sampling methods are techniques used to select a subset
(sample) from a larger population for research or analysis.
• They help ensure that the sample accurately represents
the population while reducing time and cost constraints.
• Sampling methods fall into two main categories:
probability sampling and non-probability sampling.
2
Sampling Techniques
3
Probability Sampling (Random)
• Probability sampling is a method of selecting a sample
where every individual in the population has a known and
equal chance of being chosen.
• It is widely used in statistical and scientific research to
ensure that the sample is representative of the population.
• Since the selection process is random, it reduces bias
and allows for generalization of results to the entire
population.
4
Key Features
• Based on random selection
• Every individual has an equal chance of being chosen
• Allows for statistical generalization
• Reduces selection bias
• Requires a complete list of the population (sampling
frame)
5
Advantages
• Minimizes Selection Bias – Since participants are selected randomly,
there is little to no researcher bias in the selection process.
• Ensures Representativeness – The sample reflects the
characteristics of the entire population, improving accuracy.
• Allows for Statistical Inference – Researchers can apply probability
theory to analyze data and make predictions about the entire
population.
• Reproducible and Reliable – Results obtained from probability
sampling can be repeated and verified by other researchers.
• Suitable for Large Populations – It is particularly useful when
studying large groups, ensuring diversity and fairness.
6
Disadvantages
• Time-Consuming and Costly – Collecting data randomly
requires a complete population list (sampling frame),
making it expensive and complex.
• Requires a Large Population – It may not be practical
for small or specific populations where listing all members
is difficult.
• May Not Capture Specific Subgroups Well – If
subgroups are too small, they might be underrepresented
unless stratified sampling is used.
• Complex Execution – Techniques like stratified or cluster
sampling require additional steps and careful planning.
7
Types of Probability Sampling Methods
• Simple Random Sampling (Lottery method, random
number generator)
• Systematic Sampling (Selecting every nth individual)
• Stratified Sampling (Dividing the population into
subgroups)
• Cluster Sampling (Selecting entire groups randomly)
8
Simple Random Sampling
• Simple Random Sampling (SRS) is a probability sampling
method where every individual in the population has an
equal chance of being selected.
• The selection process is completely random, often done
using lottery methods, random number generators, or
computer software.
• This method is commonly used in research where
fairness and unbiased representation are essential.
9
Example
• If a school has 500
students and the
researcher wants to select
50 students for a survey,
• they can assign each
student a number from 1
to 500 and use a random
number generator to
select 50 numbers.
• Each student
corresponding to those
numbers will be part of the
sample.
10
Advantages
• Unbiased Selection – Each individual has an equal
chance of being selected, reducing the risk of bias.
• Easy to Understand and Implement – The method is
simple and requires minimal technical knowledge.
• Representative Sample – When the population is
homogeneous, the sample is likely to represent the entire
population accurately.
• Allows Statistical Inference – The data collected can be
used to make generalizations about the population.
11
Disadvantages
• Time-Consuming and Costly – It can be difficult to
conduct if the population is large or widely spread out.
• Requires Complete Population List – A comprehensive
list of the population (sampling frame) is necessary, which
is not always available.
• Risk of Unrepresentative Sample – In heterogeneous
populations, simple random sampling might not capture
small subgroups adequately.
• Not Always Practical – Manually randomizing large
populations can be tedious without software assistance.
12
Systematic Sampling
• Systematic Sampling is a probability sampling method
where individuals are selected at regular intervals from an
ordered list.
• The first participant is chosen randomly, and then every
nth individual is selected, where "n" is the sampling
interval.
• This method is simpler than simple random sampling and
ensures even coverage of the population.
13
14
Example
• A researcher wants to survey 100 students from a school
of 1,000 students. The sampling interval is calculated as:
• The researcher randomly selects a starting student (e.g.,
5th student) and then selects every 10th student (15th,
25th, 35th, etc.) until the sample of 100 is complete.
15
Advantages
• Simple and Quick – Easier to implement than simple
random sampling.
• Even Distribution – Ensures a well-spread-out sample
across the population.
• Less Prone to Human Bias – Since selection follows a
fixed interval, it reduces researcher bias.
• Good for Large Populations – Useful when dealing with
large lists or databases.
16
Disadvantages
• Risk of Pattern Bias – If the population has a hidden
pattern that aligns with the sampling interval, it may lead
to biased results.
• Not Completely Random – Unlike simple random
sampling, some individuals have no chance of selection.
• Requires a Sampling Frame – A complete list of the
population is necessary.
17
Stratified Sampling
• Stratified Sampling is a probability sampling method
where the population is divided into distinct subgroups
(strata) based on a shared characteristic (e.g., age,
gender, income level).
• A random sample is then drawn from each stratum in
proportion to its size in the population.
• It involves dividing your population into homogeneous
subgroups (strata) and then taking a simple random
sample in each subgroup.
• This method ensures that all subgroups are adequately
represented in the final sample.
18
19
Example
• A researcher wants to survey 200 students from a school
with 1,000 students, categorized as:
• Grade 9: 300 students
• Grade 10: 250 students
• Grade 11: 200 students
• Grade 12: 250 students
20
Advantages
• Ensures Representation – Guarantees that all
subgroups are proportionally included.
• More Precise than Simple Random Sampling –
Reduces variability within each subgroup, leading to
better estimates.
• Allows for Subgroup Analysis – Enables comparisons
across different strata.
• Reduces Sampling Bias – Prevents underrepresentation
of minority groups in the population.
21
Disadvantages
• Requires Population Information – A complete list of the
population and subgroup classifications is necessary.
• Complex and Time-Consuming – Requires additional
steps, such as identifying and dividing strata.
• Not Effective for Homogeneous Populations – If the
population lacks significant differences, stratification may
not be useful.
22
Cluster Sampling
• Cluster Sampling is a probability sampling method where
the population is divided into groups (clusters), and a
random selection of clusters is chosen.
• Instead of selecting individuals randomly from the entire
population, researchers randomly select entire clusters
and include all individuals within those clusters in the
sample.
• It is useful when the population is large and
geographically dispersed.
23
24
Example
• Imagine a company wants to conduct an employee
satisfaction survey across 500 office branches
worldwide. Instead of surveying employees from all
branches, they use Cluster Sampling:
• Divide the population into clusters – Each office branch
is considered a cluster.
• Randomly select clusters – The company randomly
picks 50 office branches from the 500.
• Survey all employees – All employees in the selected
branches participate in the survey.
25
Advantages
• Cost-Effective and Time-Saving – Reduces costs by
focusing on selected clusters instead of the entire
population.
• Easier to Implement – Useful when a complete list of
individuals is unavailable, but groups (clusters) are
identifiable.
• Suitable for Large Populations – Ideal for large-scale
research where surveying the entire population is
impractical.
26
Disadvantages
• Higher Sampling Error – Since fewer clusters are
surveyed, the results may be less representative.
• Risk of Homogeneity Within Clusters – If members
within a cluster are too similar, it may lead to biased
results.
• Less Precision Compared to Stratified Sampling – The
randomness within clusters can lead to variability in
results.
27
Multi-Stage Sampling
• Multi-stage sampling is a type of sampling method
where the population is divided into multiple stages or
levels to gradually select the final sample.
• Instead of directly selecting individuals from the whole
population, selection happens in multiple stages —
making the process more practical, especially for large
populations.
28
29
Non-Probability Sampling
• Non-probability sampling is a type of sampling method
where not every individual in the population has an
equal chance of being selected.
• The selection depends on the researcher's judgment,
convenience, or specific criteria rather than random
selection.
• It is mostly used in qualitative research or when the
population is hard to access.
30
Example
• If a researcher wants to know the opinions of students
about the new library system:
• The researcher only asks 20 students sitting in the library
(Convenience Sampling).
• Or asks only final-year students (Purposive Sampling).
31
Advantages
• Easy & Quick Process: Takes less time to collect data.
• Less Expensive : Suitable for small budgets.
• Useful for Small Populations: Best for small groups or
niche research.
• Flexible: Can be adjusted based on the researcher's
needs.
• Good for Exploratory Research: Helps in the early
stages of research to understand basic information.
32
Disadvantages
• Not Representative: Results may not reflect the entire
population.
• High Risk of Bias: Personal judgment can affect the
sample selection.
• Cannot Generalize Results: Findings cannot be applied
to the whole population.
• No Equal Chance for Everyone : Some people have
zero chance of being selected.
33
Difference Between Probability Sampling & Non-
Probability Sampling
Basis Probability Sampling Non-Probability Sampling
Meaning every member of the population has
an equal chance of being selected.
not every member has an
equal chance of being
selected.
Selection
Method
Random selection Based on researcher's
judgment, convenience, or
criteria
Chance of
Selection
Everyone has an equal chance Only selected individuals
have a chance
Bias Risk Very low bias High risk of bias
Accuracy Highly accurate results Less accurate results
Time Time-consuming Quick & easy
Cost Expensive Less expensive
Used For Large population surveys (Census,
Election surveys)
Small population,
Exploratory research
Result
Generalization
Can be generalized to the entire
population
Cannot be generalized
34
Convenience Sampling
• Convenience Sampling is a non-probability sampling
method where participants are selected based on their
easy availability and proximity to the researcher.
• It is called convenience because the researcher chooses
people who are easiest to reach without considering
whether they represent the whole population.
• Example: A researcher wants to know about students'
opinions on online classes. He asks only his friends in
the library because they are easily available.
35
Purposive Sampling
• Purposive Sampling (also called Judgmental
Sampling) is a non-probability sampling method where
the researcher selects participants based on specific
purpose, knowledge, or characteristics that fit the
research study.
• In this method, the researcher uses personal judgment
to choose participants who are most suitable for the study.
• Example: If a researcher wants to study the impact of
social media on business owners, He will only select
business owners with social media experience.
36
Snowball Sampling
• Snowball Sampling is a non-probability sampling
method where existing participants help the researcher to
find more participants by referring others.
• It works like a snowball rolling down a hill — the
sample size gets bigger as each participant refers more
people.
• This method is mostly used when the population is hard
to reach or hidden (like rare disease patients).
37
Quota Sampling
• Quota Sampling is a non-probability sampling method
where the population is divided into different groups or
categories based on certain characteristics (like age,
gender, education, or income).
• A fixed number of participants (quota) is selected from
each group.
• The researcher selects participants based on personal
judgment until the required number is reached.
• Example : If a researcher wants to survey 100 students
about online classes:
• 50 males, 50 females
38

Sampling techniques and its types s.sampling techniques and its typess.

  • 1.
    SAMPLING TECHNIQUES Dr.Bharath VMFM., M.Com., Ph.D Assistant Professor Kristu Jayanti College Bengaluru 1 bharath.v@kristujayanti.com
  • 2.
    Sampling Methods • Samplingmethods are techniques used to select a subset (sample) from a larger population for research or analysis. • They help ensure that the sample accurately represents the population while reducing time and cost constraints. • Sampling methods fall into two main categories: probability sampling and non-probability sampling. 2
  • 3.
  • 4.
    Probability Sampling (Random) •Probability sampling is a method of selecting a sample where every individual in the population has a known and equal chance of being chosen. • It is widely used in statistical and scientific research to ensure that the sample is representative of the population. • Since the selection process is random, it reduces bias and allows for generalization of results to the entire population. 4
  • 5.
    Key Features • Basedon random selection • Every individual has an equal chance of being chosen • Allows for statistical generalization • Reduces selection bias • Requires a complete list of the population (sampling frame) 5
  • 6.
    Advantages • Minimizes SelectionBias – Since participants are selected randomly, there is little to no researcher bias in the selection process. • Ensures Representativeness – The sample reflects the characteristics of the entire population, improving accuracy. • Allows for Statistical Inference – Researchers can apply probability theory to analyze data and make predictions about the entire population. • Reproducible and Reliable – Results obtained from probability sampling can be repeated and verified by other researchers. • Suitable for Large Populations – It is particularly useful when studying large groups, ensuring diversity and fairness. 6
  • 7.
    Disadvantages • Time-Consuming andCostly – Collecting data randomly requires a complete population list (sampling frame), making it expensive and complex. • Requires a Large Population – It may not be practical for small or specific populations where listing all members is difficult. • May Not Capture Specific Subgroups Well – If subgroups are too small, they might be underrepresented unless stratified sampling is used. • Complex Execution – Techniques like stratified or cluster sampling require additional steps and careful planning. 7
  • 8.
    Types of ProbabilitySampling Methods • Simple Random Sampling (Lottery method, random number generator) • Systematic Sampling (Selecting every nth individual) • Stratified Sampling (Dividing the population into subgroups) • Cluster Sampling (Selecting entire groups randomly) 8
  • 9.
    Simple Random Sampling •Simple Random Sampling (SRS) is a probability sampling method where every individual in the population has an equal chance of being selected. • The selection process is completely random, often done using lottery methods, random number generators, or computer software. • This method is commonly used in research where fairness and unbiased representation are essential. 9
  • 10.
    Example • If aschool has 500 students and the researcher wants to select 50 students for a survey, • they can assign each student a number from 1 to 500 and use a random number generator to select 50 numbers. • Each student corresponding to those numbers will be part of the sample. 10
  • 11.
    Advantages • Unbiased Selection– Each individual has an equal chance of being selected, reducing the risk of bias. • Easy to Understand and Implement – The method is simple and requires minimal technical knowledge. • Representative Sample – When the population is homogeneous, the sample is likely to represent the entire population accurately. • Allows Statistical Inference – The data collected can be used to make generalizations about the population. 11
  • 12.
    Disadvantages • Time-Consuming andCostly – It can be difficult to conduct if the population is large or widely spread out. • Requires Complete Population List – A comprehensive list of the population (sampling frame) is necessary, which is not always available. • Risk of Unrepresentative Sample – In heterogeneous populations, simple random sampling might not capture small subgroups adequately. • Not Always Practical – Manually randomizing large populations can be tedious without software assistance. 12
  • 13.
    Systematic Sampling • SystematicSampling is a probability sampling method where individuals are selected at regular intervals from an ordered list. • The first participant is chosen randomly, and then every nth individual is selected, where "n" is the sampling interval. • This method is simpler than simple random sampling and ensures even coverage of the population. 13
  • 14.
  • 15.
    Example • A researcherwants to survey 100 students from a school of 1,000 students. The sampling interval is calculated as: • The researcher randomly selects a starting student (e.g., 5th student) and then selects every 10th student (15th, 25th, 35th, etc.) until the sample of 100 is complete. 15
  • 16.
    Advantages • Simple andQuick – Easier to implement than simple random sampling. • Even Distribution – Ensures a well-spread-out sample across the population. • Less Prone to Human Bias – Since selection follows a fixed interval, it reduces researcher bias. • Good for Large Populations – Useful when dealing with large lists or databases. 16
  • 17.
    Disadvantages • Risk ofPattern Bias – If the population has a hidden pattern that aligns with the sampling interval, it may lead to biased results. • Not Completely Random – Unlike simple random sampling, some individuals have no chance of selection. • Requires a Sampling Frame – A complete list of the population is necessary. 17
  • 18.
    Stratified Sampling • StratifiedSampling is a probability sampling method where the population is divided into distinct subgroups (strata) based on a shared characteristic (e.g., age, gender, income level). • A random sample is then drawn from each stratum in proportion to its size in the population. • It involves dividing your population into homogeneous subgroups (strata) and then taking a simple random sample in each subgroup. • This method ensures that all subgroups are adequately represented in the final sample. 18
  • 19.
  • 20.
    Example • A researcherwants to survey 200 students from a school with 1,000 students, categorized as: • Grade 9: 300 students • Grade 10: 250 students • Grade 11: 200 students • Grade 12: 250 students 20
  • 21.
    Advantages • Ensures Representation– Guarantees that all subgroups are proportionally included. • More Precise than Simple Random Sampling – Reduces variability within each subgroup, leading to better estimates. • Allows for Subgroup Analysis – Enables comparisons across different strata. • Reduces Sampling Bias – Prevents underrepresentation of minority groups in the population. 21
  • 22.
    Disadvantages • Requires PopulationInformation – A complete list of the population and subgroup classifications is necessary. • Complex and Time-Consuming – Requires additional steps, such as identifying and dividing strata. • Not Effective for Homogeneous Populations – If the population lacks significant differences, stratification may not be useful. 22
  • 23.
    Cluster Sampling • ClusterSampling is a probability sampling method where the population is divided into groups (clusters), and a random selection of clusters is chosen. • Instead of selecting individuals randomly from the entire population, researchers randomly select entire clusters and include all individuals within those clusters in the sample. • It is useful when the population is large and geographically dispersed. 23
  • 24.
  • 25.
    Example • Imagine acompany wants to conduct an employee satisfaction survey across 500 office branches worldwide. Instead of surveying employees from all branches, they use Cluster Sampling: • Divide the population into clusters – Each office branch is considered a cluster. • Randomly select clusters – The company randomly picks 50 office branches from the 500. • Survey all employees – All employees in the selected branches participate in the survey. 25
  • 26.
    Advantages • Cost-Effective andTime-Saving – Reduces costs by focusing on selected clusters instead of the entire population. • Easier to Implement – Useful when a complete list of individuals is unavailable, but groups (clusters) are identifiable. • Suitable for Large Populations – Ideal for large-scale research where surveying the entire population is impractical. 26
  • 27.
    Disadvantages • Higher SamplingError – Since fewer clusters are surveyed, the results may be less representative. • Risk of Homogeneity Within Clusters – If members within a cluster are too similar, it may lead to biased results. • Less Precision Compared to Stratified Sampling – The randomness within clusters can lead to variability in results. 27
  • 28.
    Multi-Stage Sampling • Multi-stagesampling is a type of sampling method where the population is divided into multiple stages or levels to gradually select the final sample. • Instead of directly selecting individuals from the whole population, selection happens in multiple stages — making the process more practical, especially for large populations. 28
  • 29.
  • 30.
    Non-Probability Sampling • Non-probabilitysampling is a type of sampling method where not every individual in the population has an equal chance of being selected. • The selection depends on the researcher's judgment, convenience, or specific criteria rather than random selection. • It is mostly used in qualitative research or when the population is hard to access. 30
  • 31.
    Example • If aresearcher wants to know the opinions of students about the new library system: • The researcher only asks 20 students sitting in the library (Convenience Sampling). • Or asks only final-year students (Purposive Sampling). 31
  • 32.
    Advantages • Easy &Quick Process: Takes less time to collect data. • Less Expensive : Suitable for small budgets. • Useful for Small Populations: Best for small groups or niche research. • Flexible: Can be adjusted based on the researcher's needs. • Good for Exploratory Research: Helps in the early stages of research to understand basic information. 32
  • 33.
    Disadvantages • Not Representative:Results may not reflect the entire population. • High Risk of Bias: Personal judgment can affect the sample selection. • Cannot Generalize Results: Findings cannot be applied to the whole population. • No Equal Chance for Everyone : Some people have zero chance of being selected. 33
  • 34.
    Difference Between ProbabilitySampling & Non- Probability Sampling Basis Probability Sampling Non-Probability Sampling Meaning every member of the population has an equal chance of being selected. not every member has an equal chance of being selected. Selection Method Random selection Based on researcher's judgment, convenience, or criteria Chance of Selection Everyone has an equal chance Only selected individuals have a chance Bias Risk Very low bias High risk of bias Accuracy Highly accurate results Less accurate results Time Time-consuming Quick & easy Cost Expensive Less expensive Used For Large population surveys (Census, Election surveys) Small population, Exploratory research Result Generalization Can be generalized to the entire population Cannot be generalized 34
  • 35.
    Convenience Sampling • ConvenienceSampling is a non-probability sampling method where participants are selected based on their easy availability and proximity to the researcher. • It is called convenience because the researcher chooses people who are easiest to reach without considering whether they represent the whole population. • Example: A researcher wants to know about students' opinions on online classes. He asks only his friends in the library because they are easily available. 35
  • 36.
    Purposive Sampling • PurposiveSampling (also called Judgmental Sampling) is a non-probability sampling method where the researcher selects participants based on specific purpose, knowledge, or characteristics that fit the research study. • In this method, the researcher uses personal judgment to choose participants who are most suitable for the study. • Example: If a researcher wants to study the impact of social media on business owners, He will only select business owners with social media experience. 36
  • 37.
    Snowball Sampling • SnowballSampling is a non-probability sampling method where existing participants help the researcher to find more participants by referring others. • It works like a snowball rolling down a hill — the sample size gets bigger as each participant refers more people. • This method is mostly used when the population is hard to reach or hidden (like rare disease patients). 37
  • 38.
    Quota Sampling • QuotaSampling is a non-probability sampling method where the population is divided into different groups or categories based on certain characteristics (like age, gender, education, or income). • A fixed number of participants (quota) is selected from each group. • The researcher selects participants based on personal judgment until the required number is reached. • Example : If a researcher wants to survey 100 students about online classes: • 50 males, 50 females 38