Questions
1. What is the difference between a parameter and a statistic?
2. Which three kinds of non-probability sample exist?
3. In a study about patients in psychiatric institutions in The Netherlands, a sample is drawn as follows: First, one draws at random a number of institutions from the full list of Dutch psychiatric institutions. Then, a number of patients is drawn at random from each of the selected institutions. What kind of sampling procedure is described here?
4. A researcher wants to know to what extent alcohol use is associated with study results. She puts a note on the bulletin board to ask students who drink to participate in the study. 33 students sign up. What kind of sampling procedure is described here?
5. What is meant with the so-called selection bias?
Answers
1. What is the difference between a parameter and a statistic?
A parameter refers to a value that describes the population. A statistic refers to a value that describes the sample.
2. Which three kinds of nonprobability sample exist?
Convenience sample
Quota sample
Purposive sample
3. In a study about patients in psychiatric institutions in The Netherlands, a sample is drawn as follows: First, one draws at random a number of institutions from the full list of Dutch psychiatric institutions. Then, a number of patients is drawn at random from each of the selected institutions. What kind of sampling procedure is described here?
A cluster sample.
When it is difficult to receive information beforehand about how many and what kind of individuals are present n the population, cluster sampling is commonly used. In this case, the researcher does not draw individuals directly from the population, but from clusters of possible participants, such as regions within a country. Often, ‘multistage sampling’ is used with cluster sampling. With multistage sampling, one determines large clusters first. Then, smaller clusters within the large clusters are determined. This process continues until a sample is drawn, with participants randomly drawn from each cluster.
4. A researcher wants to know to what extent alcohol use is associated with study results. She puts a note on the bulletin board to ask students who drink to participate in the study. 33 students sign up. What kind of sampling procedure is described here?
A nonprobability sample (or convenience sample).
In some situations it is not possible or awkward to draw a chance-sample. In that case, a ‘nonprobability’ sample is drawn. With nonprobability samples, one does not know how representative the sample is for the population. Many psychological studies for example are performed on the basis of samples that may not be representative for the population.
5. What is meant with the so-called selection bias?
This implies that the way in which the participants are selected may lead to a biased image. Imagine for example online questionnaires. People who do not have access to the internet, are automatically excluded from the study.
