You often need to know if two things are related. For example, does more study time lead to better test scores? Does a person’s height relate to their weight? A Pearson correlation test helps you answer these questions. It tells you the strength and the direction of the relationship between two continuous variables.
At SPSS Solutions, we want to make sure you know how to run this test correctly. Once you have your results, you also need to report them the right way for your paper or thesis.
When to Use the Pearson Correlation Test
You use a Pearson correlation when you have two variables that are measured on a continuous scale. This means they are interval or ratio scales. Common examples include age, test scores, temperature, or reaction time. You should also make sure your data is somewhat normally distributed.
If your variables are ranked or if the data is not normal, you might need a different test like Spearman correlation. Always check your data in the Variable View before you start your analysis. Make sure both variables are set to Scale in the Measure column.
Checking Your Assumptions
Before you trust your results, you must check a few things. First, look at a scatterplot. Go to Graphs and select Chart Builder. Drag a scatterplot into the window and put your two variables on the axes. You want to see a pattern that looks roughly like a straight line. If the data looks like a curve, Pearson correlation might not be the right choice.
Second, make sure there are no extreme outliers. An outlier is a data point that is very far away from the rest of your group. One single outlier can change your correlation result by a lot. Check this by looking at your scatterplot or by running a boxplot.
How to Run the Test in SPSS
Running the test is simple if you follow these steps:
- Click on Analyze in the top menu.
- Select Correlate.
- Click on Bivariate.
- Move your two variables into the Variables box.
- Make sure the Pearson box is checked under Correlation Coefficients.
- Click OK.
SPSS will create a table in the output window. This table is called the Correlations matrix.
Understanding the SPSS Output
When you look at your output, you will see a box with your variables listed in both the rows and columns. The number you need to look for is the Pearson Correlation coefficient. This number, often called r, will be between -1 and +1.
- A value of 0 means there is no relationship.
- A value of +1 means there is a perfect positive relationship. As one variable goes up, the other goes up.
- A value of -1 means there is a perfect negative relationship. As one variable goes up, the other goes down.
You also need to look at the Sig. (2-tailed) value. This is your p-value. If this number is less than .05, your result is statistically significant. This means it is unlikely that the relationship you found happened just by chance.
How to Report Results in APA 7 Style
When you write about your findings, you need to be clear. You should report the r value, the sample size, and the p-value. If your p-value is very small, like .000 in SPSS, you should report it as p < .001.
Here is an example of how to write it in your paper:
A Pearson correlation was conducted to examine the relationship between study time and test scores. The results showed a significant positive relationship between the two variables, r(48) = .65, p < .001. This suggests that students who studied for more hours tended to earn higher scores on the final exam.
In this example, the number in the parentheses, which is 48, stands for the degrees of freedom. For a correlation, this is your total sample size minus 2.
Common Mistakes to Avoid
One big mistake is saying that correlation means causation. Just because two things move together does not mean one causes the other. For example, ice cream sales and sunburns might correlate because both happen more often in the summer. Eating ice cream does not cause a sunburn.
Another mistake is ignoring the strength of the relationship. A result can be statistically significant even if the correlation is weak. Always look at the r value to see if the relationship is actually strong enough to matter in the real world.
If you have more than two variables you want to test at once, you might eventually need to perform more complex tests like a SPSS One-Way ANOVA Tutorial to look for group differences. Keep your analyses focused on your specific research questions.
FAQs
What if my p-value is greater than .05?
If your p-value is greater than .05, it means your result is not statistically significant. You cannot say there is a relationship between your variables based on this test.
Do I need to report the exact p-value?
In APA style, you generally report p values to two or three decimal places. If the output shows .000, you should write it as p < .001 to show that the p-value is very small.
Can I use Pearson for ordinal data?
No, you should use Spearman correlation if your data is ordinal. Pearson is strictly for continuous data. Using the wrong test can lead to results that do not make sense.
If you need more help with your data, visit SPSS Solutions to find other tutorials and guides. Taking the time to understand your output will make your research much stronger.