Stratified Random Sampling

STRATIFIED RANDOM SAMPLING – A representative number of

subjects from various subgroups is randomly selected.

Suppose we wish to study computer use of educators in the Hartford system.

Assume we want the teaching level (elementary, middle school, and high
school) in our sample to be proportional to what exists in the population of
Hartford teachers.

First we must determine what percentage of the teachers in the Hartford

system are elementary, middle school, and high school. For this example, we
will use 50%, 20% and 30% respectively. Because those percentages exist in
our population, we want our sample to have the same percentages.

Let’s also assume that we want to sample 200 teachers. Since 50% of those
teachers need to be elementary teachers, we need 100 elementary teachers
in our sample (200 X .50). To achieve this, we obtain a list of all of the
elementary teachers in the system. From that list we randomly select 100.

Similarly, we use a list of all of the middle school teachers and randomly

select 40 (20% of 200). We do the same for the high school teachers and
select 60.

The sample we selected is exactly proportional to the population with regards

to teaching level. If we had not used STRATIFIED RANDOM SAMPLING we
might have reached a similar proportion, or by chance, we might have had
over representation of one of the groups.
Understanding Stratified Samples and How
to Make Them
By Ashley Crossman
Updated on January 27, 2020

A stratified sample is one that ensures that subgroups (strata) of a given

population are each adequately represented within the whole sample
population of a research study. For example, one might divide a sample of
adults into subgroups by age, like 18–29, 30–39, 40–49, 50–59, and 60 and
above. To stratify this sample, the researcher would then randomly select
proportional amounts of people from each age group. This is an effective
sampling technique for studying how a trend or issue might differ across
subgroups.

Importantly, strata used in this technique must not overlap, because if they
did, some individuals would have a higher chance of being selected than
others. This would create a skewed sample that would bias the research and
render the results invalid.

Some of the most common strata used in stratified random sampling include
age, gender, religion, race, educational attainment, socioeconomic status, and
nationality.

When to Use Stratified Sampling

There are many situations in which researchers would choose stratified
random sampling over other types of sampling. First, it is used when the
researcher wants to examine subgroups within a population. Researchers
also use this technique when they want to observe relationships between two
or more subgroups, or when they want to examine the rare extremes of a
population. With this type of sampling, the researcher is guaranteed that
subjects from each subgroup are included in the final sample, whereas
simple random sampling does not ensure that subgroups are represented
equally or proportionately within the sample.

Proportionate Stratified Random Sample

In proportional stratified random sampling, the size of each stratum is
proportionate to the population size of the strata when examined across the
entire population. This means that each stratum has the same sampling
fraction.

For example, let’s say you have four strata with population sizes of 200, 400,
600, and 800. If you choose a sampling fraction of ½, this means you must
randomly sample 100, 200, 300, and 400 subjects from each stratum
respectively. The same sampling fraction is used for each stratum regardless
of the differences in population size of the strata.

Disproportionate Stratified Random Sample

In disproportionate stratified random sampling, the different strata do not have
the same sampling fractions as each other. For instance, if your four strata
contain 200, 400, 600, and 800 people, you may choose to have different
sampling fractions for each stratum. Perhaps the first stratum with 200 people
has a sampling fraction of ½, resulting in 100 people selected for the sample,
while the last stratum with 800 people has a sampling fraction of ¼, resulting
in 200 people selected for the sample.

The precision of using disproportionate stratified random sampling is highly

dependent on the sampling fractions chosen and used by the researcher.
Here, the researcher must be very careful and know exactly what they are
doing. Mistakes made in choosing and using sampling fractions could result in
a stratum that is over-represented or under-represented, resulting in skewed
results.

Advantages of Stratified Sampling

Using a stratified sample will always achieve greater precision than a simple
random sample, provided that the strata have been chosen so that members
of the same stratum are as similar as possible in terms of the characteristic of
interest. The greater the differences between the strata, the greater the gain in
precision.
Administratively, it is often more convenient to stratify a sample than to select
a simple random sample. For instance, interviewers can be trained on how to
best deal with one particular age or ethnic group, while others are trained on
the best way to deal with a different age or ethnic group. This way the
interviewers can concentrate on and refine a small set of skills and it is less
timely and costly for the researcher.

A stratified sample can also be smaller in size than simple random samples,
which can save a lot of time, money, and effort for the researchers. This is
because this type of sampling technique has a high statistical precision
compared to simple random sampling.

A final advantage is that a stratified sample guarantees better coverage of the

population. The researcher has control over the subgroups that are included
in the sample, whereas simple random sampling does not guarantee that any
one type of person will be included in the final sample.

Disadvantages of Stratified Sampling

One main disadvantage of stratified sampling is that it can be difficult to
identify appropriate strata for a study. A second disadvantage is that it is more
complex to organize and analyze the results compared to simple random
sampling.

Updated by Nicki Lisa Cole, Ph.D.

How to use stratified random
sampling to your advantage
13 min read
Stratified random sampling helps you pick a sample that reflects the groups in your
participant population. Our ultimate guide gives you a clear definition, example, and
process for doing it yourself.

When it comes to statistical surveys and getting the data you need, there’s no shortage of
sampling techniques you can use.
Simple sampling, systematic sampling, quota sampling, cluster sampling — there are numerous
methods for designing a sample to represent your population of interest.

Of course, each varies in accuracy, reliability, and efficiency. No two methods are the same and
some are more complicated than others.

In this article, we’re going to focus on one in particular: stratified random sampling. We’re going
to highlight what it is, how you can use it to your advantage, and several best-practice tips to
help you get going.

Definition — what is stratified

random sampling?
Stratified random sampling (also known as proportional random sampling and quota random
sampling) is a probability sampling technique in which the total population is divided into
homogenous groups (strata) to complete the sampling process.

Each stratum (the singular for strata) is formed based on shared attributes or characteristics —
such as level of education, income and/or gender. Random samples are then selected from each
stratum and can be compared against each other to reach specific conclusions.

For example, a researcher might want to know the correlation between income and education —
they could use stratified random sampling to divide the population into strata and take a random
sample from it.
Stratified random sampling is typically used by researchers when trying to evaluate data from
different subgroups or strata. It allows them to quickly obtain a sample population that best
represents the entire population being studied.

Stratified random sampling is one of four probability sampling techniques: Simple random
sampling, systematic sampling, stratified sampling, and cluster sampling.

Of course, your choice of sampling technique will depend on your goals, budget, and desired
level of accuracy. With this in mind, make sure to clearly outline what it is you want to achieve
and try out different methods to see which work best for your research.

But for now, where do you start with stratified random sampling?

Process — How do you do stratified

random sampling?
1. Define the strata needed for your sample.
Strata are usually created based on the differences between participant’s shared characteristics –
e.g. their race, gender, nationality, level of education, or age group. Researchers may or may not
already have prior knowledge about a population’s shared characteristics.

2. Define your sample size.

It’s important to define the ratio numbers of your sample so it is proportionally representative of
the total population (see the FAQ section below for more information).

3. Randomly select from each stratum.

After stratifying each member of the population into relevant subsections, you will apply random
sampling techniques to randomly select participants from each stratum. Potential sampling
methods for random selection include simple random sampling or systematic random sampling.

4. Review stratum results.

When done correctly, stratified random sampling will provide a final sample that is exhaustive
(each participant of the population must belong to one stratum) and mutually exclusive (where
participants don’t overlap with another stratum).

5. Combine all stratum samples into one representative sample.

For an accurate, representative sample of the entire population, you must combine all stratum
examples into one. This will allow you to carry out a total population analysis.

Why do researchers use stratified

random sampling?
Researchers use stratified random sampling when they are already aware of (or have become
aware of) subdivisions within a population that need to be accounted for in their research. This
leads to several advantages and disadvantages:

Advantages of stratified random sampling

 Stratified random sampling gives you a systematic way of
gaining a population sample that takes into account
the demographic make-up of the population, which leads to
stronger research results.
 The method is fair for participants as the sample from each
stratum can be randomly selected, meaning there is no bias in
the process.
 As participant grouping must be exhaustive and mutually
exclusive, stratified random sampling removes variation and
the chances of overlap between each stratum.
 Lastly, it helps with efficient and accurate data collection.
Having a smaller, more relevant sample to work with means
a more manageable and affordable research project.

Disadvantages of stratified random sampling

  Researchers may hold prior knowledge of the population’s
shared characteristics beforehand, which increases the risk
for selection bias when strata are defined.
 There is more administration to do to conduct this process, so
researchers must include this extra time and order.
 When randomly sampling each stratum, the resulting sample
may not be representative of the full population. It is worth
reviewing the results to see if the sample is proportional to
the whole population.
 Once you have the final sample, data analysis of the
information becomes more complicated to take into account
the layers of the stratum.

If you’re worried about errors in your sampling, this article can help.

Example — Stratified random

sampling in action
Let’s look at an example to bring this method to life:

If we’re investigating wage differences between genders, we can stratify a larger population into
different genders (e.g. female and male) or pay grades (e.g. under $50k, $50-100k, $100-250k,
over $250k).

If we choose to stratify by gender and randomly select a sample across each of the gender
groups, then these samples can be compared using pay grades to explore wage gaps.

So in the example below, the total population is 15. When gender is applied to the population, we
can see there are more men (9) than women (6). This gives us a sample ratio of 2:1, or a sample
fraction of ⅔ men to ⅓ women.

If we want a sample size of 5 (one-third of the total population), we must randomly select
participants in proportion to the size of each stratum. The number of participants selected must
reflect the sample ratio.
Image as originally seen on Scribbr

As a result, the final sample will have 5 randomly selected participants, which will be split by
gender (made up of 2 women and 3 men).

Frequently asked questions (FAQs)

about stratified random sampling
What is the difference between stratified random sampling and
cluster sampling?
Let’s explore cluster sampling vs stratified random sampling.

What is cluster sampling?

There are three forms of cluster sampling: one-stage, two-stage and multi-stage.

One-stage cluster sampling first creates groups, or clusters, from the population of participants
that represent the total population. These groups are based on comparable groupings that exist –
e.g. zip codes, schools or cities.
The clusters are randomly selected, and then sampling occurs within these selected clusters.
There can be many clusters and these are mutually exclusive, so participants don’t overlap
between the groups

Two-stage cluster sampling first randomly selects the cluster, then the participants are randomly
selected from within that cluster.

Multi-stage cluster sampling is a more complex process which involves dividing the population
into groups before one or more clusters are chosen at random and sampled.
 

The main difference between stratified sampling and cluster sampling is that with cluster
sampling, there are natural groups separating your population. In cluster sampling, the sampling
unit is the whole cluster. Instead of sampling individuals from each group, a researcher will
study whole clusters.

In stratified random sampling, however, a sample is drawn from each strata (using a random
sampling method like simple random sampling or systematic sampling). Elements of each of the
samples will be distinct, giving the entire population an equal opportunity to be part of these
samples. Typically, natural groups do not exist, so you divide your target population into groups
(stratum).

Generally, cluster sampling is much more affordable and “efficient”, whereas stratified random
sampling is more precise.

Image as originally seen on Scribbr

What is the difference between stratified random sampling and

simple random sampling?
Let’s explore simple random sampling vs stratified random sampling.
What is simple random sampling?

Simple random sampling selects a smaller group (the sample) from a larger group of the total
number of participants (the population). It’s one of the simplest systematic sampling methods
used to gain a random sample. Simple random sampling relies on using a selection method that
provides each participant with an equal chance of being selected. And, since the selection
process is based on probability and a random selection, the smaller sample is more likely to be
representative of the total population and free from researcher bias. This method is also called a
method of chance.
 

Simple random sampling involves randomly selecting data from the entire population so each
possible sample is likely to occur. There are no constraints with this method and therefore no
bias.

Stratified random sampling, on the other hand, divides the population into smaller groups (strata)
based on shared characteristics. A random sample is then taken from each (in direct proportion to
the size of the stratum compared to the population) and combined to create a random sample.

Image as originally seen on Scribbr

What should be the size of the sample chosen from each

stratum?
The size of the sample you select will vary based on several factors:
  Scale
In general, to analyse and draw meaningful conclusions, you
need a large sample that can provide you with sufficient data
from the total population.
 Practicality
From a practical standpoint, if you have a larger population,
you want to also have a sample size that does not require a lot
of administration to collect and manage.
 Accuracy
You want a sample size that is going to accurately represent
the total population to make the findings as truthful as
possible.

With stratified random sampling, you will end up with a sample that is proportionally
representative to the population based on the stratum used.

In most cases, this will work well. However, you may need to vary the proportions manually if
you’re aware of additional information that could skew the results.

For instance, using our wage example from above, the sample has 5 randomly selected
participants, which will be split by gender (made up of 2 women and 3 men). If you’re aware that
the wage gap range is larger across men, then this sample may miss key information as you don’t
have enough male data to support the reality.

In this case, you may want to:

Either, adjust the sample ratio to include more men – e.g. from 2:1 (6 men to 3 women) to 3:1 (8
men to 2 women).
Or, increase the sample size to include more of the population, to better reflect the wage range in
the male proportion of the sample – e.g. increasing the sample size from 5 to 10.

If you’re unsure where to start, try our sample size calculator to get a good indication.

Conclusion: Where to go next to

learn more?
And that’s stratified random sampling. Hopefully, you now have a good idea of how to use this
probability sampling technique to aid your research and surveys.

But what if you want to simplify the process further by using a research panel?
If you’re thinking of using a research panel instead of conducting research yourself, you may
way to read our in-depth eBook: The Panel Management Guide

In it, we discuss how you can:

 Ensure the right panel size

 Create the right profiling questions
 Optimise contact frequency
 Identify the key indicators of a healthy panel
 Find out how rewards and incentives can benefit your
surveys
Stratified Random Sampling: Definition,
Method and Examples

Stratified Random Sampling: Definition

Stratified random sampling is a type of probability sampling using which
a research organization can branch off the entire population into multiple non-
overlapping, homogeneous groups (strata) and randomly choose final
members from the various strata for research which reduces cost and
improves efficiency. Members in each of these groups should be distinct so
 that every member of all groups get equal opportunity to be selected using
simple probability. This sampling method is also called “random quota
sampling”.

Select your respondents

Age, socioeconomic divisions, nationality, religion, educational achievements

and other such classifications fall under stratified random sampling.

Let’s consider a situation where a research team is seeking opinions about

religion amongst various age groups. Instead of collecting feedback from
326,044,985 U.S citizens, random samples of around 10000 can be selected
for research. These 10000 citizens can be divided into strata according to
age,i.e, groups of 18-29, 30-39, 40-49, 50-59, and 60 and above. Each
stratum will have distinct members and number of members.

Learn more: Demographic Segmentation

8 Steps to select a stratified random sample:

1. Define the target audience.
2. Recognize the stratification variable or variables and figure out the number
of strata to be used. These stratification variables should be in line with the
objective of the research. Every additional information decides the
stratification variables. For instance, if the objective of research to
understand all the subgroups, the variables will be related to the subgroups
and all the information regarding these subgroups will impact the
variables. Ideally, no more than 4-6 stratification variables and no more than
6 strata should be used in a sample because an increase in stratification
variables will increase the chances of some variables canceling out the
impact of other variables.
3. Use an already existent sampling frame or create a frame that’s inclusive of
all the information of the stratification variable for all the elements in the
target audience.
4. Make changes after evaluating the sampling frame on the basis of lack of
coverage, over-coverage, or grouping.
5. Considering the entire population, each stratum should be unique and
should cover each and every member of the population. Within the stratum,
the differences should be minimum whereas each stratum should be
 extremely different from one another. Each element of the population should
belong to just one stratum.
6. Assign a random, unique number to each element.
7. Figure out the size of each stratum according to your requirement. The
numerical distribution amongst all the elements in all the strata will
determine the type of sampling to be implemented. It can either be
proportional or disproportional stratified sampling.
8. The researcher can then select random elements from each stratum to form
the sample. Minimum one element must be chosen from each stratum so
that there’s representation from every stratum but if two elements from each
stratum are selected, to easily calculate the error margins of the calculation
of collected data.
Learn more: Simple Random Sampling

Types of Stratified Random Sampling:

 Proportionate Stratified Random Sampling:
In this approach, each stratum sample size is directly proportional to the
population size of the entire population of strata. That means each
strata sample has the same sampling fraction.
Proportionate Stratified Random Sampling Formula: nh = ( Nh / N ) * n
nh= Sample size for hth stratum

Nh= Population size for hth stratum

N = Size of entire population

n = Size of entire sample

If you have 4 strata with 500, 1000, 1500, 2000 respective sizes and the
research organization selects ½ as sampling fraction. A researcher has to
then select 250, 500, 750, 1000 members from the respective stratum.
Stratum A B C D
Population Size 500 1000 1500 200
Sampling Fraction 1/2 1/2 1/2 1/2
Final Sampling Size Results 250 500 750 100
 Irrespective of the sample size of the population, the sampling fraction will
remain uniform across all the strata.

Learn more: Systematic Sampling

 Disproportionate Stratified Random Sampling:

Sampling fraction is the primary differentiating factor between the
proportionate and disproportionate stratified random sampling. In
disproportionate sampling, each stratum will have a different sampling
fraction.

Stratum A B C D
Population Size 500 1000 1500 2000
Sampling Fraction 1/2 1/3 1/4 1/5
Final Sampling Size Results 250 333 375 400
The success of this sampling method depends on the researcher’s precision
at fraction allocation. If the allotted fractions aren’t accurate, the results may
be biased due to the overrepresented or underrepresented strata.  
Learn more: Cluster Sampling

Stratified Random Sampling Examples:

Researchers and statisticians use stratified random sampling to analyze
relationships between two or more strata. As the stratified random sampling
involves multiple layers or strata, it’s crucial to calculate the strata before
calculating the sample value.

Learn more: Quantitative Market Research

Following is a classic stratified random sampling example:

Let’s say, 100 (Nh) students of a school having 1000 (N) students were asked
questions about their favorite subject. It’s a fact that the students of the 8th
grade will have different subject preferences than the students of the 9th
grade. For the survey to deliver precise results, the ideal manner is to divide
each grade into various strata.
 Here’s a table of the number of students in each grade:
Grade Number of students (n)
5 150
6 250
7 300
8 200
9 100

Calculate the sample of each grade using the stratified random

sampling formula:

Stratified Sample (n5) = 100 / 1000 * 150 = 15

Stratified Sample (n6) = 100 / 1000 * 250 = 25
Stratified Sample (n7) = 100 / 1000 * 300 = 30
Stratified Sample (n8) = 100 / 1000 * 200 = 20
Stratified Sample (n9) = 100 / 1000 * 100 = 10
Learn more: Convenience Sampling

Advantages of Stratified Random Sampling:

 Better accuracy in results in comparison to other probability sampling methods
such as cluster sampling, simple random sampling, and systematic
sampling or non-probability methods such as convenience sampling. This
accuracy will be dependent on the distinction of various strata, i.e., results
will be highly accurate if all the strata are extremely different.
 Convenient to train a team to stratify a sample due to the exactness of the
nature of this sampling technique.
 Due to statistical accuracy of this method, smaller sample sizes can also
retrieve highly useful results for a researcher.
 This sampling technique covers maximum population as the researchers
have complete charge over the strata division.
Learn more: Cluster Sampling vs Stratified Sampling
When to use Stratified Random Sampling?
 Stratified random sampling is an extremely productive method of sampling
in situations where the researcher intends to focus only on specific strata
from the available population data. This way, the desired characteristics of
the strata can be found in the survey sample.
 Researchers rely on this sampling method in cases where they intend to
establish a relationship between two or more different strata. If this
comparison is conducted using simple random sampling, there is a higher
likelihood of the target groups being not equally represented.
 Samples with a population which are difficult to access or contact, can be
easily be involved in the research process using the stratified random
sampling technique.
 The accuracy of statistical results is higher than simple random sampling
since the elements of the sample and chosen from relevant strata. The
diversification within the strata will be much lesser than the diversification
which exists in the target population. Due to the accuracy involved, it is
highly probable that the required sample size will be much lesser and that
will help researchers in saving time and efforts.
Select your respondents