Planning and organisationSampling methods

Researchers need to collect enough primary research to have a clear idea of the views and opinions of the people who are relevant to their research. The people relevant to the research are often referred to as a population.

Example

If your school was planning to change its opening hours, the population would be made up of:

• children
• parents
• teachers
• governors
• staff
• any relevant stakeholders

If your school was very small, the researcher would be able to ask everyone their views. However, if your school was very large, it may be difficult to ask everyone their views, so the researcher may decide to ask only a sample of the population.

Although the sample is a smaller number, the people questioned should still be representative of the overall population.

Representative means that the sample has similar characteristics to the whole population. So if the whole population has 51% of females, then the smaller sample should also include 51% of females.

There are three stages to sampling:

1. Who are the people you want to sample?
2. How many people are to be sampled?
3. How are people going to be sampled? (ie which method should you choose?)

This means that the sample only reflects the characteristics of the smaller population. As a sample is always less than the whole population, a sample has the following advantages because it:

• reduces costs
• saves on time
• requires fewer resources

Types of samples

Convenience sampling

This involves gathering information from whoever is available when the research takes place. For example, if you were carrying out research about the catering facilities in your school, a convenience sample would involve walking around school and asking whoever you met to complete your questionnaire.

Random sampling

This is a sample in which each person has an equal chance of being selected. It can be done by pulling names out of a hat or using a computer to generate numbers. For example, if you were carrying out research about the catering facilities in your school, a random sample would mean every person in the school would have an equal chance of being selected.

Stratified random sampling

This involves dividing the population into segments and then taking a random sample from each segment. For example, if you were carrying out research about the catering facilities in your school, a stratified sample would involve you dividing up the school into different groups. This could include girls aged 10-12 and 13-16, and boys aged 10-12 and 13-16. A random sample from each group would then be taken in order to complete your questionnaire.

Judgement sampling

This is where samples are chosen by researchers because they feel that they give them the information they require. For example, if you were carrying out research about the catering facilities in your school, a judgement sample may involve you deciding who uses the canteen most and then asking them to complete your questionnaire.

It is important that the sampling method chosen will produce information that is representative of the population. This is called generalisability.

Generalisability refers to the extent to which we can apply the findings of our research to the target population we are interested in.