Home / Statistics – Tutorial / Statistics – Stratified Sampling

Stratified Sampling

A probability sampling technique in which the researcher divides the entire population into different subgroups (strata), then randomly selects the final items proportionally from the different strata(must be non-overlapping).Stratified sampling is also known as proportional sampling or quota sampling.We use strata like age, gender, socioeconomic status, religion, nationality and educational attainment.

Steps for Stratified sampling:

Divide the population into smaller strata, based on shared attributes and characteristics of the members.

Select a random sample from each stratum in a number that is proportional to the size of the stratum.

To form a random sample,pool the subsets of the strata together.

Types of Stratified Sampling:

Proportionate Stratified Random Sampling:

The sample size of each stratum is proportionate to the respective population sizewhen viewed against the entire population i.e., each stratum has the same sampling fraction.

Example:

we have 3 strata with 100, 200 and 300 population sizes respectively. Let sampling fraction be ½. Then, weshould randomly sample 50, 100 and 150 subjects from each stratum respectively.

Stratum	A	B	C
Population Size	100	200	300
Sampling Fraction	½	½	½
Final Sample Size	50	100	150

Disproportionate Stratified Random Sampling:

With disproportionate sampling, the different strata have different sampling fractions.

Advantages:

Highlighting a specific subgroup within the population.

Observing existing relationships between two or more strata.

This allows the researcher to sample the rare extremes (eventhe smallest and most inaccessible) subgroupsof the given population.

When there is homogeneity within strata and heterogeneity between strata, the estimates can be of higher statistical precision.

Due to precision, it requires a small sample size which saves a lot of time, money and effort of the researchers.

Disadvantages:

This sampling requires the knowledge of distinguishing between strata in the sample frame

Research process may take longer and more expensive due to the extra stage in the sampling procedure.

If mistakes happen in allotting sampling fractions, a stratum may either be overrepresented or underrepresented which will result in skewed results adding further complexity.

Suppose for a survey, we need 50 students who are either juniors or seniors in a high school.

Based on gender,