Midterm 1 - Sampling Flashcards
What is Type I Error?
When the study reports an effect between variables in a sample, but in the whole population of interest, there isn’t a difference
What is a Type II Error?
When the study does not report an effect between variables in a sample, but in the whole population, there is a difference
What are the 4 types of probability sampling?
- Simple random sample
- Stratified random sample
- Cluster sampling
- Multi-stage sampling
What is probability sampling?
- Taking a sample of subjects that is representative of the entire population of interest
- Each person in the population of interest has an equal chance of being in the sample
What is non-probability sampling?
- Where samples are gathered in a process which does not give each person in the population equal chance of being selected
What are the 3 types of non-probability sampling?
- Convenience Sampling
- Purposive Sampling
- Quota Sampling
What is Simple Random Sampling?
- Every member of the population has an equal chance of being selected for the sample
Methods:
- Names in a hat
- Random numbers table
- SPSS can select a random number of people from a list
What are the strengths and weaknesses of Simple Random Sampling?
Strengths;
- Easy to carry out
- Large sample size representative of the population
- No information needed before sampling
Weaknesses;
- Large samples often needed
- Small sample often unrepresentative of the population
- Comparisons between small subgroups may be difficult
What is Stratified Random Sampling?
- Involves dividing the population into groups based on a known characteristic (age, gender, socio-economic group)
- A sample is then drawn, using a simple random sampling technique, from each group to mirror the proportional representation of each division of the population
What are the strengths and weaknesses of Stratified Random Sampling?
Strengths;
- Fewer people needed to achieve the same representativeness
- Can customise sample to be comparable to a wider population
- Can make inferences about smaller subgroups
Weaknesses;
- Requires obtaining information on the particular dividing variables (age, gender, sex)
- Becomes difficult if there are different stratification variables
What is Cluster Random Sampling?
- The sampling unit is not a person but a cluster of people belonging to a “naturally occurring group”
- The clusters may be space-based, such as naturally occurring geographical or physical units (school, school year, school class)
- This would be appropriate for a school base intervention (whether a newly structured PE lesson increased activity levels in the class)
What is multistage sampling?
- Divides large populations into stages to make the sampling process more practical
What is Convenience Sampling?
- The sampling unit is individuals and they are selected purely on easy/convenience
- Therefore, not all individuals have the same probability of being selected
Strengths and weaknesses of Convenience Sampling?
Strengths;
- Quick and easy compared to probability sampling
- Mostly used for pilot studies
Weaknesses;
- Can’t estimate sampling error, therefore can’t make inferences about the whole population based on your sample
- Exclusion bias (gender in sport sciences)
- Cannot generalise from the sample to the population of interest
What is Purposive Sampling?
- Sampling unit is individuals and individuals are selected because they possess a particular characteristic of interest or they represent a specific group (e.g. Brexit: opinions of hardcore remainers vs hardcore leavers). Therefore, not all individuals have the same probability of being selected