Issues in Probability & Non-Probability Sampling

An error occurred trying to load this video.

Try refreshing the page, or contact customer support.

Coming up next: How to Determine Sample Size

You're on a roll. Keep up the good work!

Take Quiz Watch Next Lesson
Your next lesson will play in 10 seconds
  • 0:05 Sampling
  • 2:04 Random Error
  • 2:59 Systematic Error
  • 5:36 Nonresponse Error
  • 6:58 Lesson Summary
Save Save Save

Want to watch this again later?

Log in or sign up to add this lesson to a Custom Course.

Log in or Sign up

Speed Speed

Recommended Lessons and Courses for You

Lesson Transcript
Instructor: Natalie Boyd

Natalie is a teacher and holds an MA in English Education and is in progress on her PhD in psychology.

Choosing a sample is an important part of research. The two methods of sampling both come with their own set of issues. In this lesson, we'll look at the issues with probability and non-probability sampling.


Mickey is a psychologist who is curious about how color affects people's attitudes. He believes that if a person fills out a job satisfaction survey on a pastel-colored piece of paper, then she will mark that she's more satisfied with her job than if she fills it out on a neon-colored piece of paper.

In order to test his theory, Mickey puts together a survey and prints it out on pastel paper and then prints it out on neon paper. Now all he has to do is choose a group of people to give the survey to and see if the pastel-paper people mark that they are more satisfied with their jobs than the neon-paper people.

Sampling is the process whereby a researcher chooses the subjects for his or her study. There are two major types of sampling: probability sampling, which involves choosing subjects randomly to participate in the study, and non-probability sampling, which involves choosing subjects non-randomly to participate in the study.

Sampling is important because the goal of choosing a group of subjects is to be able to say that what they do generalizes to the population as a whole. If you choose a group of subjects, or a sample, that does not represent the population, your results might not generalize well.

Issues in sampling occur when there ends up being a difference between the results of a sample and the results of a population. For example, perhaps Mickey does his study, and his results show that his sample participants marked that they are more satisfied with their jobs when they fill out the survey on neon-colored paper.

But in reality, if Mickey did the same study on every single worker in America, the results would show that people are happier with their jobs when they fill out the survey on pastel-colored paper. That's a problem!

The difference between the results of a sample and the results of a population is called error. Let's look at three types of error: random error, systematic error and nonresponse error.

Random Error

As we mentioned, sampling issues can cause differences between a study's sample and the population at large. Before we get to sampling issues that can do that, it's important to look at non-sampling error. Random error is any fluctuation or difference between the population and sample that are due to chance.

Random error cannot be eliminated; it will always be there. Think about this: maybe Mickey gives his pastel-colored survey to a woman who is having a particularly bad day at work. In that case, her response may be negative due to the random chance that she is having a bad day, not because of the color of the paper.

Both types of sampling, probability and non-probability, have random error. In other words, whether Mickey chooses his sample randomly or not will not affect random error. It's just always there, and there's nothing he can do about it.

Systematic Error

But there is another type of error - systematic error - that Mickey can work to reduce in his study. Systematic error is any difference between the population and sample that are due to problems with the sample. For example, imagine that Mickey goes to a big company and gives his pastel surveys to half of the workers and his neon surveys to the other half of the workers.

Except when he gave the surveys out, he did not give them out to the secretaries of the company. Perhaps the secretaries spend all day working with paper, and their tired eyes get sore from the neon paper, so they mark their satisfaction lower on that one. Or perhaps they see boring pastels and white paper all day and would give more satisfied answers on neon paper. Either way, Mickey's sample has some systematic error based on the fact that he did not include the secretaries in his sample.

There are many types of systematic error. Three common ones are:

1. Underrepresentation

This is when a demographic group is underrepresented in the sample, either because the researcher ignored them (like Mickey did with the secretaries) or because the researcher couldn't find enough subjects from that group willing to participate. For example, maybe the executives at the company are really busy and refuse to fill out the survey. The executives would be an underrepresented group.

2. Researcher bias

This occurs when the researcher selects the sample or changes something in the experiment in order to get the result he wants. For example, what if Mickey only selected the people who he believes are satisfied with their jobs to be in the pastel paper group? Or he chooses people who got bad evaluations for the neon paper group? In that case, his results might not reflect the reality of the population.

3. Inadequate sample size

When a sample is too small, it does not adequately represent the population, and systematic error increases. For example, what if Mickey just gave the sample to three people? The chances that those three people would respond in the same way that the entire population would is very small, and therefore, systematic error is high.

In general, probability sampling has a lower systematic error than non-probability sampling. This is because if you are randomly selecting your sample, the chances of you ending up with underrepresented groups or researcher bias are lower.

To unlock this lesson you must be a Member.
Create your account

Register to view this lesson

Are you a student or a teacher?

Unlock Your Education

See for yourself why 30 million people use

Become a member and start learning now.
Become a Member  Back
What teachers are saying about
Try it risk-free for 30 days

Earning College Credit

Did you know… We have over 200 college courses that prepare you to earn credit by exam that is accepted by over 1,500 colleges and universities. You can test out of the first two years of college and save thousands off your degree. Anyone can earn credit-by-exam regardless of age or education level.

To learn more, visit our Earning Credit Page

Transferring credit to the school of your choice

Not sure what college you want to attend yet? has thousands of articles about every imaginable degree, area of study and career path that can help you find the school that's right for you.

Create an account to start this course today
Try it risk-free for 30 days!
Create an account