# Sampling

Sampling:

The aim of sampling is to make generalisations beyond the individuals used in the study

Parameter = populations
Statistics = sample
Inferences are made from statistics to predict parameters

Inclusion and exclusions criteria:
Criteria or characteristics displayed by study participants as a prerequisite for being included or excluded from a study.

Sampling Methods

Census:
• whole of defined population is counted/measured

Probability sampling:
• by random selection, every unit in the population has equal chance of selection
• eliminates sampling bias
• difference between sample statistic and population parameter is the sampling error
• randomisation allows for estimation of degree of sampling error  confidence in validity

Types:
1) Simple random sampling – each selection is independent and has equal chance of selection
2) Systematic sampling – every (eg 10th) element is sampled but start is random
3) Stratified sampling – sample is divided into strata and a simple random sample is taken from each stratum

Non-probability sampling:
In these samples the probability of selection is not known  cannot estimate sampling error

Types:
1) Convenience
2) Quota
3) Snowball