6 Sample Methods in Statistics (Plus Examples)

By Indeed Editorial Team

June 17, 2021

A sample in statistics is important for determining relevant information about groups of people. Trying to collect data on each individual in a study can be time-consuming, and samples allow statisticians to create more manageable data sets. If you take samples for statistics or want to be a statistician, you may want to learn more about how samples are useful. In this article, we cover what samples are, list methods for obtaining them and provide examples of various samples and uses for them.

Related: How To Become a Data Analyst

What are samples in statistics?

A statistical sample is a smaller set of data taken from a larger one to represent the whole. Statisticians use samples when analyzing and gathering data because it's difficult to manage extensive sets of data at once. For example, if a statistician is trying to determine how many American households use candles, it may be difficult to gather data from every household. Gathering that data from a smaller set and using it to make reasonable assumptions about the whole might be a more efficient way of analyzing data.

Related: 10 Jobs for Statistics Majors

Methods for obtaining samples in statistics

Samples are important for statisticians to make calculations and predictions. Here are some methods they may use to collect samples:

  • Cluster random: In this method of sampling, a statistician splits the target group into several smaller groups. Statisticians may either select random people for the sample or deliberately choose certain people.

  • Convenience: A convenience sampling is when statisticians collect data from the most readily available source. This method of gathering data is usually not random.

  • Simple random: The simple random method of sampling typically uses a computer or other reliable technology to help randomly select subjects from which to gather information. Every individual within a data set has an equal chance of being selected as part of the sample.

  • Stratified random: In a random stratified sample, the statistician divides a target group into various groups depending on specific criteria. They then select an equal number of individuals from each group to be part of the sample.

  • Systematic random: This is when statisticians order individuals within a data set by some specific aspect—whether it be name, age or financial status—and then select a random starting point within the line. The statistician then determines a value by which they include individuals. For example, every 20 people might mark a new entry in the data set.

  • Voluntary response: A voluntary response sample only collects data from participants who provide their information. These results can be unreliable because many people who willingly participate in surveys share common traits.

Related: What Is a Sampling Distribution? Definition and Types of Distribution

Examples of statistical samples

Statistical samples can be useful in many industries and can allow people to gather and analyze data without assessing each individual in a group. Here are some examples of statistical samples that use the methods described above:

Cluster random

A movie theater wants to gather information about their customers' experiences. Using randomization software, they select three random showings throughout the day of different movies. They then ask the guests from these movies to complete a survey as they exit. This method of sample collection is usually a reliable sampling technique.


A radio show wants to gather public opinions about a celebrity event. They place a booth along a busy sidewalk and interview those who stop when walking by. When doing this, they discover that more than half of the people they interview approve of a certain celebrity's choices.

This kind of sample is usually not as effective as other methods in representing an intended group because there are many aspects that can affect the outcome of the information. The route they take, the city they're in and the time of day at which the radio station conducts their interviews can make the sample less representative of the intended group.

Simple random

An internet company uses an online randomizer to select 100 of their 1,000 customers to survey about their internet needs. The company wants to determine whether they should invest in new internet technology. This method of sampling is typically reliable, and as samples grow larger, their reliability grows, too.

Stratified random

A university wants to gather information about their student body's preferences for homecoming festivities. To gather a fair representation of information from each major, they survey 10% of students from each discipline. So, because there are 2,000 chemistry majors at the school, they only survey 200 of them. This ensures fair representation for all majors.

Systematic random

A company gathers a list of employers and orders them from longest employment history to those with the shortest. After choosing a random place in the list to begin, the company counts six names down the line and adds each name to the selected sample. They then gather information about this group as a sample.

Voluntary response

A financial institution wants to gather more information about its customer service team's performance. To determine this, they offer a survey at the end of each customer service call in which clients can participate if they want to. This is typically not an effective way of gathering information, as clients may be more likely to participate in the survey if they feel disgruntled or experienced issues. Satisfied customers are not as likely to participate in the survey, making the gathered data not as representative of the entire customer group.

Related: What Are Demographics? (Definition, Examples and Uses)

Uses for statistical samples

Here are some industries that often use samples when conducting research to gather and analyze data for large groups:

  • Science: Scientists often collect information from small groups to determine the effects of pollution, climate change or water quality, for example.

  • Marketing: A marketing team may gather samples of its client base to determine which campaigns have been most successful.

  • Government: Certain governments may want to determine which citizens or geographical areas require new roads or other government services.

  • Economics: These professionals may gather samples to determine how the economic atmosphere affects people in varying areas and of varying financial statuses.

  • Medicine: Doctors or medical researchers may conduct clinical trials with small samples of a population to determine whether a drug or vaccine is safe to administer.

Browse more articles