maths sampling

Simple random sampling

Every possible sample of a given size has an equal chance of being picked

Example: random number generator

Advantages and disadvantages of simple random

A- produce unbiased sample

D- hard to do in practice, requires list of entire population and everyone to respond, time consuming, expensive

Opportunity sampling

Choosing respondents based upon their availability and convenience

Example: asking people waiting at a bus stop

Advantages and disadvantages of opportunity

A- Cheap and convenient

D- may not be generalisable

Systematic sampling

Taking participants at regular intervals from a list of the population

Example: calling the person at the top of each page in a phone book

Advantages and disadvantages of systematic

A- avoids unwanted clustering of data, practically easier than using random number generators

D- requires list of entire population, is less random than simple random as no longer independent

Stratified sampling

Splitting population into groups based on factors relevant to research then random sampling from each group in proportion to the size of that group

Advantages and disadvantages of stratified

A- produces a sample representative over the factors identified

D- requires list of entire population with additional info about each member, time consuming, expensive, determining which factors to consider isn’t always easy

Quota sampling

Splitting population into groups based on factors relevant to research then opportunity sampling from each group

Example: sampling 100 men and women in a supermarket to find out their spending

Advantages and disadvantages of quota

A- ensures sample is representative over factors identified

D- may not be generalisable

Cluster sampling

Splitting population into groups called clusters based on convenience then randomly choosing some clusters to study further

Example: sampling five countries at random to find the life expectancy

Advantages and disadvantages of cluster sampling

A- cheaper and easier than other random methods

D- less accurate as clusters may not be representative