× FreshBooks
Official App

Statistical Sampling

Save Time Billing and Get Paid 2x Faster With FreshBooks

Try It Free ➝

# Stratified Random Sampling: Definition, Types & Examples

In statistical sampling, a representative subset from a population is selected in such a way that the sample statistics (i.e., the survey results) are as close as possible to the population statistics (i.e., the values if we were able to survey every member of the population).

Stratified random sampling process is one type of statistical sampling that helps you achieve this objective. Stratified random sampling method involves dividing a population into mutually exclusive and collectively exhaustive strata.

This method of sampling cannot subdivide further and is exhaustive because they include all possible members of that subgroup.

And assigning probability proportional to size (PROSC) sampling weights to each stratum before selecting the final sample.

A stratified random sample differs from simple random sampling technique in that it partitions a population first based on relevant identifiable characteristics or ‘strata’, which means it is also cluster sampling. Table of Contents

KEY TAKEAWAYS

• Researchers can use stratified random sampling to get a representative sample of the entire population under study.
• Stratified random sampling is the division of a population into homogeneous strata.
• Stratified random sampling is different from simple random sampling. It involves random selections of data from a whole population. Each possible sample is therefore equally likely.

## What Is Stratified Random Sampling?

A stratified random sample is a type of statistical sampling in which a population divides into mutually exclusive and collectively homogeneous strata.

Probability sampling is then used to select the random sample from each stratum. A stratified random sample differs from simple random sampling in that it first partitions the population into mutually exclusive and collectively exhaustive strata based on relevant identifiable characteristics and then selects a sample from each stratum through probability sampling.

In simple random sampling, all members of the population have an equal chance of selection, regardless of the characteristics they possess.

In stratified random sampling, members of the population belonging to each stratum have a greater chance of selection than those who do not.

This type of probability sampling helps avoid disproportionate sampling in your stratum sample size.

## How Stratified Random Sampling Works

To understand how a stratified random sampling formula works, let’s take a look at an example. Imagine a researcher is conducting a survey to learn about the income levels of various groups in the country.

He has identified three mutually exclusive and collectively exhaustive subgroups: income less than \$25,000, \$25,000-\$50,000, and \$50,000 or more.

He then divides the population of the country according to these subgroups and randomly selects a sample from each stratum. This means members of the first subgroup have a greater chance of selection than members of the other two subgroups because there are fewer people in the first subgroup.

The researcher can also use cluster sampling to select the sample, which means he can survey households or geographical areas instead of a sample of individuals. The advantage of this approach is that it reduces sampling variability because the researcher uses the same sample for every subgroup.

## Types of Stratified Random Sampling

There are a couple different types of stratified random sampling. They are equal probability proportionate to size (EPTS) sampling and disproportionate stratified sampling.

Equal probability proportionate to size (EPTS) sampling divides the population into mutually exclusive and collectively exhaustive strata (meaning they cannot be subdivided further and are exhaustive because they include all possible members of that subgroup), and assigns a sampling weight to each stratum before selecting the sample.

Disproportional stratified sampling (DPS) is a type of sampling that uses a proportional formula to determine the sampling weights for the strata. This formula includes the number of cases in the strata, the desired sample size, and the proportion of cases in each strata.

Sampling weight is the size of the subgroup relative to the total population. Once the subgroups are identified and weighted, the sample is drawn randomly from each subgroup. Stratified sampling is a type of probability sampling where the population is divided into mutually exclusive subgroups.

Stratified sampling is one of the most common forms of non-probability sampling. It’s called non-probability sampling because the sampling is done based on the relative size of each subgroup and not based on a random selection process.

But the most common type is probably proportional stratified random sampling, where a population divides into strata, and then the random sample is taken from each stratum in proportion to its size.

For example, if the entire population is 60% female and 40% male, then the sample would be 60% female and 40% male.

Another common method of sampling is called quota stratified random sampling. In this method, the entire population first gets divided into strata, and then a certain number of items are randomly selected from each stratum, regardless of the size of the stratum.

For example, if the entire population is divided into strata A, B, and C, and the quota random for each stratum is 5, then 5 items would be randomly selected from stratum A, 5 items would be randomly selected from stratum B, and 5 items would be randomly selected from stratum C.

There are also other types of stratified random sampling schemes, such as systematic stratified random sampling.

Here, a population gets divided into strata before choosing a random starting point within each stratum. Items are then selected at regular intervals until you meet the random quota sampling for that stratum.

Each sample provides greater insight into the subject matter researched. The type of sampling method you use depends on the outcome you want.

## Advantages of Stratified Random Sampling

There are several notable benefits to stratified random sampling, including:

• More reliable and less expensive than other types of sampling methods
• Improved precision and ability to generalize survey results
• Easier to identify certain characteristics within a subgroup
• Allows researchers to select a sample that represents the different socio-economic characteristics of the subgroups

## Disadvantages of Stratified Random Sampling

The drawbacks to using stratified random sampling are:

• Adds complexity in terms of designing and conducting the survey
• More difficult to identify members of the population belonging to specific subgroups

## Example of Stratified Random Sampling

A researcher wants to survey the general population of a country but wants to make sure that his results are representative of different socio-economic levels.

He divides the population into mutually exclusive and collectively exhaustive strata and then uses cluster sampling to select a sample from each stratum.

For example, he divides the population into low, middle, and high-income groups and then uses simple random sampling to select a sample from each group.

The researcher then surveys the selected households in each subgroup. Since he has a sample from each subgroup, his survey results will be representative of all the socio-economic levels in the general population.

## Summary

Stratified random sampling is a type of random sampling of a population divided into strata and then the random sample is taken from each stratum.

There are several types of stratified random sampling, the most common being proportional and quota stratified random sampling.

This metric can benefit you by allowing you to focus your resources on a specific population. It can also help to improve the accuracy of your results.

## FAQs About Stratified Random Sampling

Why we use stratified random sampling?

Stratified sampling is a useful sampling technique to use when you have a homogenous population that consists of subgroups. Stratified sampling is a more efficient sampling unit than SRS when the target population is large.

Is stratified sampling non probability?

Many people believe that stratified sampling is a non-probability sampling technique because accurate samples are drawn from each subgroup of a population based on the relative size of that subgroup.

However, in stratified sampling, each subgroup of a population is still given a sampling probability sampling design, which is proportionate sampling.

How is stratified random sampling used in research?

Stratified random sampling is used to select a representative sample from a heterogeneous population. It is also used when the sample size requirement for a study is unknown and where the population is too large to be surveyed with SRS.

Stratified sampling can be used when you want to focus on a specific group that represents a significant part of the population.

What is the difference between stratified and random sampling?

The simple random sample represents the entire population. It randomly selects people from the population. A stratified, random sample on the other side, divides the population into smaller groups or strata based on common characteristics.

Statistical Sampling

#### Browse Glossary Term

553 HRS

SAVE UP TO 553 HOURS EACH YEAR BY USING FRESHBOOKS

\$ 7000

SAVE UP TO \$7000 IN BILLABLE HOURS EVERY YEAR

30M+

OVER 30 MILLION PEOPLE HAVE USED FRESHBOOKS WORLDWIDE  