Sampling tech
Non-probability Sampling
not every element of the population has the opportunity for selection in the sample.
More likely to produce a biased sample.
Ex: convenience sampling, snowball sampling, Purposive Sampling
Probability Sampling – a probability sample is one in which each element of the population has a
known non-zero probability of selection.
Increases sample’s representativeness of the population.
Ex: simple random sampling, systematic sampling, stratified sampling
a) Non-probability Sampling
Convenience Sampling
element selection is based on ease of accessibility.
Least reliable, cheapest, easiest
Ex. Informal pools of friends and neighbours, on the street interviews…
Advantage: Disadvantage:
Saves time and money No way to determine representativeness
Snowball Sampling
Study respondents recruit future subjects from among their acquaintances, grow like a rolling
snowball.
Ex. homelesses, illegal workers, young drinkers, etc.)
Advantage: Disadvantage:
Low cost Community bias
Purposive Sampling
judgemental or expert’s choice sampling
Advantage: Disadvantage:
Easy to approach participants Researcher bias
B) Probability Sampling
Simple Random Sampling
equal chance of being selected
Advantage:
Unbiased
Easy to implement with random dialing.
Disadvantage:
Requires the complete list of population elements (no one must be excluded)
Time consuming
High cost
Larger sample needed
Systematic Sampling
kth name from the list
Advantage:
Simple to design
Disadvantage:
May be biased due to periodicity: may pick similar cases rather than completely random ones
Stratified Sampling
population into at least two groups strata
May be proportional or disproportional.
Advantage:
Provides data to analyze subgroups
Enables use of different methods in strata
Disadvantage:
High cost
