Stratified Random Sampling is a sampling technique used in statistics that involves dividing a population into distinct subgroups, known as strata, based on certain characteristics or attributes. The strata are mutually exclusive and collectively exhaustive, meaning that each unit in the population belongs to only one stratum and that all units together make up the entire population.


Stratified Random Sampling involves the following steps:

  1. Identify the relevant stratification criteria: Determine the characteristic(s) based on which the population can be divided into mutually exclusive strata.
  2. Determine the sample size: Decide on the desired number of samples to be selected from each stratum.
  3. Select the samples from each stratum: Randomly choose the required number of samples from each stratum, without any bias or preference.
  4. Combine the samples: Merge the selected samples from each stratum to obtain the final representative sample for analysis.


Stratified Random Sampling offers several advantages over other sampling methods:

  • Increased precision: By dividing the population into homogeneous subgroups, stratification reduces the variability within each stratum, resulting in more precise estimates.
  • Better representation: Each stratum is represented proportionally in the sample, ensuring that smaller, yet important, subgroups are not overlooked.
  • Flexibility: Stratification allows for specific analyses and comparisons within each stratum, providing more detailed insights.
  • Efficiency: By focusing efforts on relevant strata, stratified sampling can be more efficient than simple random sampling.


Despite its advantages, Stratified Random Sampling also has some limitations:

  • Requires prior knowledge: Identifying appropriate stratification criteria relies on having prior knowledge about the population characteristics.
  • Complexity in implementation: Properly carrying out stratified sampling requires careful planning and execution, which can be time-consuming and labor-intensive.
  • Potential for sampling errors: If the strata are not accurately defined or the sampling within each stratum is not random, sampling errors may occur, affecting the validity of the results.
  • Possible cost implications: Stratified Random Sampling may be more expensive to implement compared to simpler sampling methods.