sampling techniques Flashcards
sampling
A population is the set of people from the general population that we are interested in. Most research is investigating a particular group rather than everyone.
Studies can rarely be done on whole target populations meaning samples have to be taken of the people who take part in the research and predictions can then be made about the whole target population.
This sample needs to be representative of that population. If it does not represent the target population, it is said to be a biased sample.
The size of the sample is important in making sure it represents the whole population.
random sampling
Every person in the target population has an equal chance of being chosen to take part in the study.
Will involve gaining details of everyone in that population and choosing them without any bias.
E.g. pulling names out of a hat.
Very low bias as there is no choice in who participates.
High generalisability so should be representative.
systematic sampling
Involves taking the nth person from a list to create a sample.
Involves calculating the size of the population and then assessing what size the sample needs to be to work out what the sampling interval is.
Low bias and high generalisability.
stratified sampling
A small scale reproduction of the population.
Involves dividing the population into characteristics important for the research, e.g. age, sex. A random sample is then taken from these sub-sets. This ensures that the sample is representative of the population.
Low bias and high generalisability.
opportunity sampling
Using the people who happen to be available for your research.
May often be family or friends, or people in the street
Most common method of sampling.
Has effect of being quick and easy, however is most biased method.
High bias and low generalisability.
volunteer sampling
When participants volunteer to take part, usually by answering an advertisement.
Has the advantage of reaching a large number of potential participants.
Unlikely to result in a representative sample.
High bias and low generalisability.
