# Topic C7 — Sampling

## Table of contents

## Sampling methods

### Simple random sampling

- All observation have the same probability of being sampled

### Stratified sampling

- Dividing dataset in mutually exclusive + collectively exhaustive stratas.
- Sample x% of each strata
- Advantage
- precision
- every strata represented

### Cluster sampling

- Dividing dataset in mutually exclusive + collectively exhaustive clusters
- Randomly select some clusters
- Advantage: cost

## Sampling distribution

- Drawing samples gives you a
*single distribution of values of X* - Each sample produces a
*sample mean* - If you draw multiple samples, you get multiple means, called a
*sampling distribution*

Will converge to the mean of pop $ \mu $

Standard error of sample mean $\frac{\sigma}{\sqrt{n}}$

If the population is normal, then the sampling distribution is also normal, thus we can standardiye it.