Negative Correlation in Psychology: Examples, Definition & Interpretation
Instructor: Yolanda Williams
Yolanda has taught college information technology and literacy, and has a master's in counseling psychology and business administration.
Explore the relationship between positive and negative correlations. Learn about the characteristics of a negative correlation, how to determine the strength of a correlation, and more.
What Is Negative Correlation?
If you look at the data closely, you will begin to notice that as the number of hours spent playing video games increases, GPA decreases. In other words, there is a negative correlation between the school performance of high school students and playing video games.
Before we discuss negative correlation, we must first define correlation. A correlation is a single numerical value that describes a relationship between two things, or variables. The Pearson product moment correlation is the most common measure of correlation and is usually represented by the letter r. A correlation has two qualities: direction and strength.
The two directions of a correlation are positive and negative. In a positive correlation. both variables move in the same direction. In other words, as one variable increases, so does the other. For example, there is a positive correlation between smoking and alcohol use. As alcohol use increases, so does smoking.
When two variables have a negative correlation. they have an inverse relationship. This means that as one variable increases, the other decreases, and vice versa. Negative correlations are indicated by a minus (-) sign in front of the correlation value. In the example above, we noted that students who spent the higher amount of time playing video games each week had the lowest GPAs. As the hours spent playing video games decreased, the GPAs increased.
Some other examples of variables that are negatively correlated are:
- The weight of a car and miles per gallon: cars that are heavier tend to get less miles per gallon of gas.
- School achievement and days absent from school: people who miss more days of school tend to have lower GPAs.
- Vaccinations and illness: The more that people are vaccinated for a specific illness, the less that illness occurs.
Determining Correlation Strength
So, how do we determine the strength of a relationship? We look at the numbers. A correlation of 0 means there is no relationship between the two variables. A correlation of -1 means that there is a perfect negative relationship between the variables. Similarly, a correlation of 1 indicates that there is a perfect positive relationship. Perfect relationships rarely exist in real-life. If you find two things that are negatively correlated, the correlation will almost always be somewhere between 0 and -1.
The closer a negative correlation is to -1, the stronger the relationship between the two variables. For example, a correlation of -.85 is stronger than a correlation of -.49. The closer a positive correlation is to 1, the stronger the relationship. A correlation of .85 is stronger than a correlation of .49. The following is a list of guidelines for determining the strength of a negative correlation:
- 0: no relationship
- -.01 to -.19: little to no relationship
- -.20 to -.29: weak negative relationship
- -.30 to -.39: moderate negative relationship
- -.40 to -.69: strong negative relationship
- -.70 to -.99: very strong negative relationship
- -1: perfect negative relationship
It is the numerical value that determines the strength of a correlation, regardless of direction. A correlation of .80 has the same strength as a correlation of -.80.
Creating a Scatterplot Graph
The easiest way to visually represent a negative correlation is by creating a scatterplot using your two variables. If we take the data from our table and turn it into a scatterplot, this is what we would get: