Epidemiology: Methods of Sampling from a Population

It would normally be impractical to study a whole population, for example when doing a questionnaire survey. Sampling is a method that allows researchers to infer information about a population, without having to investigate every individual. Reducing the number of individuals in a study reduces the cost and workload, and may make it easier to obtain high quality information, but this has to be balanced against having a large enough sample size with enough power to detect a true association.

If a sample is to be used, by whatever method it is chosen, it is important that the individuals chosen are representative of the whole population. This may involve specifically targeting hard to reach groups. For example, if the electoral roll for a town was used to identify participants, some people such as the homeless would not be registered and therefore excluded from the study by default.

There are several different sampling techniques available. Calculation of sample size is addressed in the statistics section of the Part A syllabus.

1. Simple random sampling

In this case each individual is chosen entirely by chance and each member of the population has an equal chance, or probability, of being selected. One way of obtaining a random sample is to give each individual in a population a number, and then use a table of random numbers to decide which individuals to include.¹

2. Systematic sampling

Individuals are selected at regular intervals from a list of the whole population. The intervals are chosen to ensure an adequate sample size. For example, every 10th member of the population is included. This is often convenient and easy to use, although it may also lead to bias for reasons outlined below.

3. Stratified sampling

In this method, the population is first divided into sub-groups (or strata) who all share a similar characteristic. It is used when we might reasonably expect the measurement of interest to vary between the different sub-groups. Gender or smoking habits would be examples of strata. The study sample is then obtained by taking samples from each stratum.

In a stratified sample, the probability of an individual being included varies according to known characteristics, such as gender, and the aim is to ensure that all sub-groups of the population that might be of relevance to the study are adequately represented.¹

The fact that the sample was stratified should be taken into account at the analysis stage.

4. Clustered sampling

In a clustered sample, sub-groups of the population are used as the sampling unit, rather than individuals. The population is divided into sub-groups, known as clusters, and a selection of these are randomly selected to be included in the study. All members of the cluster are then included in the study. Clustering should be taken into account in the analysis.

The General Household survey, which is undertaken annually in England, is a good example of a cluster sample. All members of the selected households/ clusters are included in the survey.¹

5. Quota sampling

This method of sampling is often used by market researchers. Interviewers are given a quota of subjects of a specified type to attempt to recruit. For example, an interviewer might be told to go out and select 20 adult men and 20 adult women, 10 teenage girls and 10 teenage boys so that they could interview them about their television viewing. There are several flaws with this method, but most importantly it is not truly random.²

6. Convenience sampling

Convenience sampling is perhaps the easiest method of sampling, because participants are selected in the most convenient way, and are often allowed to chose or volunteer to take part. Good results can be obtained, but the data set may be seriously biased, because those who volunteer to take part may be different from those who choose not to.

7. Snowball sampling

This method is commonly used in social sciences when investigating hard to reach groups. Existing subjects are asked to nominate further subjects known to them, so the sample increases in size like a rolling snowball. For example, when carrying out a survey of risk behaviours amongst intravenous drug users, participants may be asked to nominate other users to be interviewed.

Bias in sampling

There are five important potential sources of bias that should be considered when selecting a sample, by whatever method:¹

1. Any changes from the pre-agreed sampling rules can introduce bias
2. Bias is introduced if people in hard to reach groups are omitted
3. Replacing selected individuals with others, for example if they are difficult to contact, also introduces bias
4. It is important to try and maximise the response rate to a survey; low response rates can introduce bias
5. If an out of date list is used as the sample frame, it may also introduce bias, if it excludes people who have recently moved to an area, for example.

Further potential problems with sampling strategies are covered in the common errors in epidemiological measurements section of this module.

Past paper questions
Sampling methods are addressed by the following MFPH Part A past paper question:

• June 2002 – Paper IA, Question 1

References

1. Farmer, R., Miller, D. and Lawrenson, R., 1996. Epidemiology and Public Health
   Medicine (4th ed.), Blackwell Science, Oxford.
2. http://www.stats.gla.ac.uk/steps/glossary/sampling.html - Accessed 20/01/09

© Helen Barratt 2009