- Do the authors totally ramdomise the sample to make it more representative of the population? How do they do this?
- This reduces bias and therefore makes the findings more generalisable.
- If a sample of convenience is used, then to reduce bias it needs to be large enough to be representative.
- Sometimes a large convenient sample may be randomised into smaller groups.
- Types of sampling are detailed in the
- Did they use statistical calculations (power calculations) to determine how many people were needed in the sample to make the findings generalisable.
- Large numbers required.
Next: Ethical issues