Sampling design

In the theory of finite population sampling, a sampling design specifies for every possible sample its probability of being drawn.

Mathematically, a sampling design is denoted by the function $P(S)$ which gives the probability of drawing a sample $S.$

An example of a sampling design

During Bernoulli sampling, $P(S)$ is given by

$P(S)=q^{N_{sample}(S)}\times (1-q)^{(N_{pop}-N_{sample}(S))}$

where for each element $q$ is the probability of being included in the sample and $N_{sample}(S)$ is the total number of elements in the sample $S$ and $N_{pop}$ is the total number of elements in the population (before sampling commenced).

See also

• Bernoulli sampling

Further reading

• Sarndal, , C.-E., Swensson, B., AND Wretman, J. (1992). Model Assisted Survey Sampling. Springer-Verlag, New York, NY.