What is Systematic Sampling?

Systematic sampling is when researchers select items from an ordered population using a skip or sampling interval.

For example, if researchers are interested in the population that attends a particular restaurant on a given day, they could set up shop at the restaurant and ask every tenth person to enter to be a part of their sample. 

They could also elect to ask the twentieth person, the thirtieth, or any other sample interval that suits the requirements of their research study.

Systematic sampling differs from simple random sampling, because in simple random sampling a sample of items is chosen at random from a population, and each item has a perfectly equal probability of being chosen. 

Simple random sampling leverages tables of random numbers or an electronic number generator to determine a sample, whereas these components are not necessary to perform systematic sampling.

When to Use Systematic Sampling Over Simple Random Sampling

Researchers should use systematic sampling instead of simple random sampling when a project is on a tight budget, or requires a short timeline.

Systematic sampling is also preferred over random sampling when the relevant data does not exhibit patterns, and the researchers are at low risk of data manipulation that will result in poor data quality.

Systematic sampling is simple to execute.

In order to perform simple random sampling, each element of the population of interest must be separately identified and selected. With systematic sampling, a sampling interval is used to select the individuals that will comprise the sample. 

If researchers are working with a small population, random sampling will provide the best results. 

However, if the size of the size of the sample that is required to perform the study increases, and researchers find themselves needing to create multiple samples from the population, these processes end up being extremely time-consuming and expensive. 

That’s why systematic sampling is the preferred sampling technique in this scenario.

If patterns are present, avoid systematic sampling. 

When there is no pattern in the data, systematic sampling is more effective than simple random sampling. 

But in circumstances where the population is not random, researchers are at risk of selecting individuals to comprise their sample that possess the same characteristics, which in turn has a negative effect on data quality. 

For example, if a farm that grows oranges has a sorting machine that is on the fritz, and every tenth orange that passes the sorting test is damaged, researchers are more likely to select a damaged orange to be a part of their sample if they use systematic sampling than if they were to use simple random sampling. This would result in a biased sample, and inherently poor data quality.

Use systematic sampling when there’s low risk of data manipulation.

Systematic sampling is the preferred method over simple random sampling when a study maintains a low risk of data manipulation. Data manipulation is when researchers reorder or restructure a data set, which can result in a decrease in the validity of the data.

If the risk of data manipulation is high, and the sampling interval that comes with systematic sampling has the potential to alter the data being collected, then a simple random sampling method is more appropriate and effective.

How to Perform Systematic Sampling

As we outline the steps for performing systematic sampling below, let’s continue with our example from above in which researchers are interested in the population that visits a particular restaurant on a given day.

Step #1: Estimate the size of the population of interest.

The first step of performing systematic sampling is to estimate the size of the population that visits the restaurant on a given day.

The researchers would be unable to know the exact size of the population, since they cannot be 100 percent confident who will visit the restaurant during the day, but they can make some informed estimate as to how many restaurant patrons they can expect to see.

In this step, you just want to determine a rough estimate of the population size.

Step #2: Determine how many people need to be in your sample.

Next, the researchers would need to determine how large their sample needs to be.

Depending on the estimate derived from step one, the size of the sample could be ten, one hundred, or even more than that -- it all depends on the desired data volume target for the research to be statistically significant. 

Step #3: Divide population size by the number of people in your sample to decide how often to stop somebody.

In this step, the researchers would take the estimated population size from step one , and divide it by the number of people that need to be in the sample from step two. 

The resulting number will be the sampling interval that the researchers should adhere to.

For example, if it’s estimated that 1,000 people visit the restaurant on a given day, and the researchers decide that they need a sample size of 100, then the would divide 1,000 by 100 to receive a sampling interval of ten.

This means that the researchers should stop every tenth person to ask them if they would be willing to participate in the study.

Step #4: Start by selecting a random individual.

It’s important to note that researchers should not start developing their sample by asking the first patron they see to participate in their study, as this would negatively impact data quality due to the fact that the process is therefore not random.

Instead, the researchers should begin by selecting a random individual, and from there choosing every tenth patron to enter the restaurant.  


As you’ve now learned, systematic sampling is a convenient and useful technique for developing samples. However, there are circumstances in which simple random sampling is still the preferred method.

Depending on the goal and format of your next research study, consider using systematic sampling so that you can potentially save some time, and some money at the same time!