Clinical Significance vs. Statistical Significance

Instructor: Emily Cummins
What does it mean if the results of a study are significant? In this lesson, we'll about the difference between statistical significance and clinical significance, and what this means for applying the results of research to the real world.

Significance in Research

What does the word 'significant' mean to you? Words like 'important' and 'meaningful' likely come to mind. While this is definitely part of it, in this lesson we're going to get a little more scientific. If you're a researcher, significance is a little more specific and, in fact, has more than one meaning.

In this lesson we'll go over two main types of significance, statistical significance and clinical significance.

Statistical Significance

The most basic way to define statistical significance is that it's the measure of whether the results of a statistical analysis meet some predetermined level of measurement, known as a p-value.

P-values are probability values. In psychology, researchers are generally comfortable with a p-value of .05, meaning that there is a 5% chance your results are due to chance instead of your experimental design. Basically, p-values tell us the probability of observing a result we think is significant but isn't actually.

Confusing? Think of it this way. You conduct an experiment testing whether caffeine before an exam improves performance. You get a p-value of .05. This means that there is a 5% chance your results were due to chance and not your experiment! However, researchers are comfortable with this because there is a 95% chance the result is because you figured something out!

This p-value of .05 is actually kind of arbitrary. It's really a convention that researchers use because we have to make a decision about significance somehow.

There are a few different factors that impact statistical significance and if we'll get a significant result. The first is sample size. In order to conduct a meaningful statistical analysis, we need a large sample size. Sample size is something that is computed based on the larger population. We also need to make sure our sample is unbiased. This means that everyone in the population has an equal chance of being selected and that your sample represents the population as a whole. Basically, the only way to do this is to get a random sample (a portion of your population selected randomly), which statisticians have equations for.

Let's take an example to illustrate this. Say you're a psychologist and you've designed an experiment to test out a new therapeutic technique that you've developed to help patients with obsessive-compulsive disorder ease their symptoms. You believe that by implementing this therapists can improve the success rates of reducing compulsive behaviors.

First, you need a sample of people with obsessive compulsive disorder from the larger population of people with this disorder. In other words, you'll use an equation to calculate the size of the sample you'll need, based on this larger population, to test this meaningfully. If your sample is too small, statistics won't work.

(Wondering how we know for sure we've gotten the exact number of the population of people with OCD? We often don't know for sure. Statisticians actually devised another equation to calculate an approximate population if necessary).

You'll also need a random sample to make sure your sample isn't biased. So, for example, you can't simply call up everyone you know who has OCD! This wouldn't be random (since these are specific people) or representative (somehow I doubt you know that many people with OCD).

You test this out, and come up with statistically significant results. So this means you've developed a new therapy that can be widely applied everywhere, right? Not so fast! Here's where we should talk about the second kind of significance.

Clinical Significance

Clinical significance is a little bit different than statistical significance. It's also known as 'clinical importance,' and this might be a helpful way to remember the difference between clinical and statistical significance. Basically, while statistical significance can give us some idea about how successful our experiment was, it cannot really tell us how important our result is out in the wider world.

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