Sampling
---------------------------------------------------------------------------------------------------------
Sampling data, even good, unbiased sampling methods can lead to “unrepresentative
samples”. A good sample is one that is “representative” of the population.
Sampling Method Definition/How Advantage Disadvantage
Every possible sample Unbiased sample Hard to predict
Simple Random has an equal chance of
being selected
Choosing respondent Cheap and May not be
Opportunity based upon their convenient generalised
availability
Taking participants at Avoids unwanted Requires entire lists of
Systematic regular intervals from a clustering of data populations
list of the population
Splitting the population Produces a sample Requires entire lists of
into groups and based on representative populations
Stratified
relevant sampling over the factor
identified
Splitting the population Ensures the May not be
into groups and sample is generalised
Quota
opportunity sampling for representative
each group
Population in groups Cheaper and Less accurate than
based on convenience easier than other other random
Cluster
and randomly choose random methods methods and may not
clusters be representational
---------------------------------------------------------------------------------------------------------
Calculation from frequency tables and grouped data
Develop Formulae ∑ fx ∑fx
x= or
∑f n
2
∑f x
2
O = = ( x)2
n
---------------------------------------------------------------------------------------------------------
Sampling data, even good, unbiased sampling methods can lead to “unrepresentative
samples”. A good sample is one that is “representative” of the population.
Sampling Method Definition/How Advantage Disadvantage
Every possible sample Unbiased sample Hard to predict
Simple Random has an equal chance of
being selected
Choosing respondent Cheap and May not be
Opportunity based upon their convenient generalised
availability
Taking participants at Avoids unwanted Requires entire lists of
Systematic regular intervals from a clustering of data populations
list of the population
Splitting the population Produces a sample Requires entire lists of
into groups and based on representative populations
Stratified
relevant sampling over the factor
identified
Splitting the population Ensures the May not be
into groups and sample is generalised
Quota
opportunity sampling for representative
each group
Population in groups Cheaper and Less accurate than
based on convenience easier than other other random
Cluster
and randomly choose random methods methods and may not
clusters be representational
---------------------------------------------------------------------------------------------------------
Calculation from frequency tables and grouped data
Develop Formulae ∑ fx ∑fx
x= or
∑f n
2
∑f x
2
O = = ( x)2
n
