Stats Sampling

Question 1

Main types of sampling methods

Answer 1

Probability (random) samplingSimple random sampling
Systematic sampling
Cluster sampling
Stratified sampling
Multistage sampling.                                   Non-probability (non-random) samplingVoluntary sampling
Convenience sampling
Snowball sampling
Quota sampling

Question 2

Quota sampling

Answer 2

Here, the population is divided into groups (strata) and then elements are selected. This is done to ensure that the sample reflects characteristics of the population. For example, a researcher may want to ensure that a sample has a proportionate representation of males and females when compared to the population from which it is drawn. It is similar to a stratified sample except that it does not involve random sampling. Elements are selected by availability and the aim is just to fill the quotas.

Question 3

Systematic sampling

Answer 3

In systematic sampling, every kth member of the population gets selected for the sample. Say you had a population of 200 and wanted a sample of 10, then every 20th member would be selected.

This could be applied to the conference example (given above) as every 20th delegate could be selected as they were leaving the conference centre at the end of the day.

Systematic sampling is easier to conduct than simple random sampling but is more prone to bias if there is a pattern in the population that is consistent with the sampling frequency. For example, imagine you wanted to sample the drinking patterns of junior doctors by estimating their weekly intake. If you selected a regular sampling time (for example monthly) this might coincide with pay day which is a time when evenings out tend to occur which would be associated with greater alcohol consumption

Question 4

Cluster sampling

Answer 4

Cluster sampling involves dividing a population into separate groups (called clusters). A random sample of clusters is then selected and each element included in the final sample.

This is really useful when clusters are located in such a way as to facilitate easy collection of data. For example, say you wanted to investigate the opinions of operating room assistants. It would be much easier to go to a selection of hospitals and interview all the assistants in one go rather than drawing up a list and travelling across the country to interview assistants located in various regions.

Question 5

Stratified sampling

Answer 5

In stratified sampling, an entire population is first divided into groups (strata) and then a random sample taken from each strata.

Strata could be groups such as males or females or age groups. This ensures that one can obtain equal numbers of different individuals.

This ensures that the final sample has certain characteristics of the population. For example, you might want to establish the different salaries of doctors. You might know that 30% of all doctors are GPs and so would obtain a sample with 30% GPs.