1.1 more likely to be representative of the
population from which they are drawn than
non-probability samples.
1.1.1 likelihood that a participant
is included in the sample is
known for each subject in
the population.
1.1.2 More commonly used
1.2 Simple random
1.2.1 each member of the population has an equal
and independent chance/probability of being
selected into the sample
1.2.2 Important principles
1.2.2.1 members of the population are
selected one at a time
1.2.2.1.1 independent of each other and
without replacement
1.2.3 i.e lottery draw iplacing each
possible number in a container
and selecting one at a time
without looking until the
desired number is reached.
1.3 Systematic
1.3.1 dividing the sampling frame into a
number of intervals, randomly selecting a
starting point and then selecting one
element from each interval in a systematic
way.
1.3.2 arranged in such a way that bias is
introduced into the sample selection
process.
1.3.2.1 i.e class list contains sub-groupings of
individuals whereby some members of the
sub-groups are never selected.
1.3.3 may select every 10th person on
the sampling list.
1.3.3.1 sampling frame is a class list arranged
in alphabetical order by surname
1.3.3.2 decide to select every fourth name on the list
1.3.3.2.1 a starting point is randomly selected between one
and four and then every fourth element is selected
1.3.3.2.2 Sample frame= divided into
intervals of four elements
2 Cluster
2.1 whole population being divided into groups or
clusters and then a certain number of clusters
are randomly sampled using simple, systematic
or stratified random sampling.
2.2 i.e geographic area, hospitals, schools
2.2.1 required number of clusters
is selected you then sample
all units within the clusters.
2.2.1.1 interested in obesity in primary school
aged children in Victoria.
2.2.1.1.1 create a sampling frame of all Victorian primary
schools and then randomly select clusters or
schools
2.2.1.1.1.1 would then invite all children to participate in the study.
2.3 very economical method of sampling.
ABS uses cluster sampling to collect data
for the National Health Survey.
3 Stratified
3.1 involves dividing the population into
groups (for example, age)
3.2 calculating the number of participants needed in
each group or strata so that the numbers reflect
their proportion in the population.
3.3 ensures that important sub-groups are
identified proportionally prior to random
sampling.
3.3.1 i.e in many community surveys people
from some ethnic groups are
under-represented.
3.3.1.1 Conduct a community survey and want Italian
population in a certain area where 20% are. So
ensure that 20% are included in the survey to be a
accurate rep.
3.4 randomly selecting participants into each stratum.