4. Population and Sample
• Population: a complete set of people with a specified set of
characteristics
• Target population: a subset of population defined by clinical and
demographic characteristics
• Accessible population: a geographically and temporally defined
subset of the target population that available for study
• Study sample: a subset of accessible population that participate
in the study
5. Why sampling is important
• Resource Constraints
• Drawing Inferences About the Population
6. 3 Features to Keep in Mind While Constructing a
Sample
Consistency
DiversityTransparency
7. Sampling Techniques
Non-probability sampling Probability Sampling
• Does not involve selection of
elements at random
• Rarely representative of the
population
• has an equal, independent
chance of being selected.
• Allows researchers to
estimate the magnitude of
sampling error (difference
between population values
and sample values)
8. Types of non-probability sampling techniques:
• Convenience sampling: selecting the most conveniently available people
as participants
• Quota sampling: identifying population strata and figuring out how many
people are needed from each stratum
• Consecutive (Snowball) sampling: recruiting all people from an
accessible population over a specific time interval
• Purposive sampling: handpicking sample members
9. Types of probability sampling techniques:
• Simple random sampling: Completely random method for selecting
subjects
• Stratified random sampling: Involves splitting subjects into mutually
exclusive groups then using use simple random method for selection
• Systematic sampling: To choose every (nth) participant from a complete list
• Cluster random sampling: To randomly select participants from a list that is
too large for simple random sampling
• Multistage random sampling: Combination of techniques
10. Bias in sampling:
• Any pre-agreed sampling rules are deviated from
• People in hard-to-reach groups are omitted
• Selected individuals are replaced with others, for example if they are difficult
to contact
• There are low response rates
• An out-of-date list is used as the sample frame (for example, if it excludes
people who have recently moved to an area)
12. Strategies to minimize sample size and
maximize power:
• Use continuous variables
• Used paired measures
• Use more precise variables
• Use unequal group sizes
• Use more common outcome
13. How to estimate sample size where there is
insufficient information:
• Extensive search
• Pilot assessment
• Clinical meaningfully detectable effect size
• Educated guess