Definition: Stratified Random Sampling

Definition 1:

In stratified random sampling, a population is divided into distinct sections or strata.  A sample is taken randomly from each stratum.  The size of the sample taken frome each stratum is in proportion to the size of that stratum in that population.

For example, a survey of 50 is required from a population of 356 people of whom 197 are men.  The population can be divided into two strata: male and female.  The proportions that should be sampled are:

Men: \displaystyle \frac {197}{356} \times 50 = 27.67

Women: \displaystyle \frac {159}{356} \times 50 = 22.33

Therefore, a stratified random sample of this population should consist of 28 men and 22 women.  Stratified random sampling has the advantage that it distributes the sample more evenly over the population.  It has the disadvantage that it requires prior knowledge of the population.

Author: ascklee

Dr. Lee teaches at the Wee Kim Wee School of Communication and Information at the Nanyang Technological University in Singapore. He founded The Mathematics Digital Library in 2013.

Leave a Reply