1.2 Random Sampling Methods

What is a random sample?

A sample where every member of the population has an equal chance of being chosen

Describe simple random sampling

Every sample of size n has an equal chance of being chosen. It requires a sampling frame (list) where every sampling element is assigned a unique number. n of the numbers are then randomly chosen by generating random numbers (using a calculator or computer).

Describe systematic sampling

The sampling elements are chosen at regular intervals from an ordered list. For example, if a sample of 50 is required from a population of 1000 then every 20th element would be chosen as 1000/50=20. Only the first element would be chosen randomly and the others would follow at equal intervals.

Describe stratified sampling

The population is divided into mutually exclusive strata (groups do not overlap) (for example by males and females or by age categories) and a random sample of equal proportion taken from each. This ensures that the proportions of selected sub-groups of the population are replicated in the sample.

What is the formula used for stratum sample size?

Stratum sample size = (number in stratum/number in population) x overall sample size

Advantages of simple random sampling

• No bias

• Cheap and easy to do for small populations and samples

• Each sampling unit has an equal and known chance of selection

Disadvantages of simple random sampling

• Not available when the population size or the sample size is large as it is potentially time consuming, disruptive and expensive

• A sampling frame is needed

Advantages of systematic sampling

• Simple and quick to use

• More suitable for large samples or populations than simple random sampling as it avoids the ‘clustering’

Disadvantages of systematic sampling

• A sampling frame is required - could be expensive to obtain and/or difficult to keep up-to-date

• Can introduce bias of the sampling frame is not random

Advantages of stratified sampling

• Sample accurately reflects the population structure

• Guarantees proportional representation of groups within a population

Disadvantages of stratified sampling

• Population must be clearly classified into distinct strata

• Selection within each stratum suffers from the same disadvantages as simple random sampling