Sampling Methods

Random Sampling

Every member has an equal chance of being selected. Use random number generators.

Pro: unbiased. Con: may not represent subgroups well.

Systematic Sampling

Select every $k$th item from a list (e.g., every 10th person).

Pro: simple, spread across population. Con: can be biased if there's a pattern.

Stratified Sampling

Divide population into groups (strata), then sample proportionally from each.

$\text{Stratum sample} = \frac{\text{stratum size}}{\text{population size}} \times \text{sample size}$

Pro: represents subgroups. Con: need to know the population structure.

A sample is biased if it doesn't represent the population fairly.

Sources of bias: convenience sampling, voluntary response, leading questions, non-response.

School has 120 boys and 80 girls. Sample of 50.

Boys: $\frac{120}{200} \times 50 = 30$. Girls: $\frac{80}{200} \times 50 = 20$.