Sampling in Research
Methodology
Steps, Criteria, Characteristics &
Types of Samples
Meaning of Sampling
• • Sampling is the process of selecting a subset
from a population.
– • It helps in drawing conclusions about the whole
population.
– • Used when population is large and complete
study is impractical.
Steps in Sample Design
• 1. Define the universe (target population).
– 2. Decide the sampling unit.
– 3. Identify the sampling frame.
– 4. Decide sample size.
– 5. Select sampling technique.
– 6. Execute the sampling process.
Criteria for Selection of Sample
• • Representativeness.
– • Adequate size.
– • Homogeneity of population.
– • Availability of resources.
– • Research objectives.
Characteristics of a Good Sample Design
• • Truly representative of population.
– • Free from bias.
– • Economical and practical.
– • High reliability and accuracy.
– • Flexible and simple to administer.
Types of Sampling
• A. Probability Sampling
– B. Non-Probability Sampling
Probability Sampling Methods
-Simple Random Sampling
– Stratified Sampling
– Systematic Sampling
– Cluster Sampling
– Multistage Sampling
Non-Probability Sampling Methods
-Convenience Sampling
– Judgment Sampling
– Quota Sampling
– Snowball Sampling
Simple Random Sampling
• • Every unit has equal chance of selection.
– • Selection is purely by chance method.
– • Lottery or random number table method used.
– • Reduces selection bias.
– • Suitable for homogeneous population.
– Example: Selecting 20 students randomly from a
class of 100.
Systematic Sampling
• • Samples selected at regular intervals.
– • Requires ordered population list.
– • First unit selected randomly.
– • Sampling interval k = N/n.
– • Simple and easy to apply.
– Example: Selecting every 10th household from a
list of 1000.
Stratified Sampling
• • Population divided into homogeneous
strata.
– • Samples drawn from each stratum.
– • Ensures representation of all subgroups.
– • Increases precision.
– • Suitable for heterogeneous population.
– Example: Selecting 60 boys and 40 girls from 100
students proportionately.
Cluster Sampling
• • Population divided into clusters
(geographical groups).
– • Entire clusters randomly selected.
– • All units in chosen clusters studied.
– • Cost-effective for large populations.
– • Less precise than stratified sampling.
– Example: Selecting 5 schools randomly and
surveying all students in them.
Multistage Sampling
• • Sampling done in multiple stages.
– • Combines different sampling techniques.
– • Large population gradually narrowed.
– • Reduces cost and complexity.
– • Used in large national surveys.
– Example: Selecting State → District → Village →
Household → Individual.
Convenience Sampling
• • Sample selected based on ease of access.
– • Respondents chosen because they are readily
available.
– • Simple and inexpensive method.
– • Does not represent entire population accurately.
– • Common in exploratory research.
– Example: Surveying students who are present in
class.
Judgment Sampling
• • Researcher selects units based on personal
judgment.
– • Also called purposive sampling.
– • Focuses on specific characteristics.
– • Useful when expert opinion is required.
– • Risk of researcher bias is high.
– Example: Selecting experienced managers for a
leadership study.
Quota Sampling
• • Population divided into categories.
– • Fixed quota assigned to each category.
– • Selection within quota is non-random.
– • Ensures representation of subgroups.
– • Faster and cheaper than stratified sampling.
– Example: Selecting 50 males and 50 females using
convenient selection.
Snowball Sampling
• • Existing respondents refer new participants.
– • Used for hard-to-reach populations.
– • Sample grows like a snowball effect.
– • Useful in social science research.
– • May lead to sampling bias.
– Example: Studying drug users through referrals
from initial participants.
Conclusion
• • Sampling is essential in research.
– • Proper sample design ensures valid results.
– • Choice of method depends on research
objectives and resources.