How you choose who is in the study
Random, systematic, stratified, convenience — and what each costs you.
Simple random — everyone in the population has an equal chance. Systematic — every k-th person on a list. Stratified — split the population into groups that matter (sex, department, severity) and sample within each, so all are represented. Cluster — sample whole units, such as wards or colleges. Convenience — whoever is available.
Why it matters
The sampling method decides who your results apply to. Convenience sampling is honest and common in postgraduate work, and it is acceptable as long as you say so and limit your conclusions accordingly. What is not acceptable is convenience sampling described as random.
An example
You need 200 nursing students from a college of 1,200 across four years.
• Convenience — the first 200 who agree in the canteen. Fast, and probably over-represents whoever eats there.
• Systematic — every 6th name on the register.
• Stratified — 50 from each year, so all four are represented even though the years differ in size.
Common mistakes
- Calling a convenience sample 'random' because you did not choose deliberately. Random has a specific meaning.
- Not stating the inclusion and exclusion criteria, so no one can tell who the results apply to.
- Ignoring the people who declined. If a quarter refused, your sample is not the population you sampled from.
Read next
- Sample size, and the four numbers it needs — Power, alpha, effect size and variability — and where each one comes from.
- Bias and confounding, in plain words — Bias is a fault in how you got your data. Confounding is a third variable explaining your result.
Chavery Research Companion applies this to your own study: it asks the questions in plain language, checks the assumptions against your data, recommends the test, and writes the sentence that reports it. Start free — planning and the master chart cost nothing.