Correlation Analysis in SPSS: Pearson and Spearman Explained
You’ve collected your data. You have two variables. And now you need to answer one crucial question: Are these two things related?
That moment of staring at your dataset, unsure which statistical test to run, is something every thesis student experiences. The good news is that correlation analysis is one of the most useful and straightforward statistical tools available—once you understand when to use Pearson versus Spearman.
At Proposal Writers Kenya, we have helped hundreds of students navigate exactly this challenge. Whether you need help running your analysis or interpreting the results, our data analysis experts are here to support you.
This guide will walk you through everything you need to know about Pearson and Spearman correlation analysis in SPSS. You’ll learn when to use each test, how to run them step by step, how to interpret the output, and how to report your findings professionally in your thesis.
What Is Correlation Analysis?
Correlation analysis measures the direction and strength of a relationship between two variables. The result is a correlation coefficient (r), which always falls between -1 and +1.
Direction tells you how the variables move together:
Positive correlation (+): Both variables increase together. Example: More study hours lead to higher exam scores.
Negative correlation (-): One variable increases as the other decreases. Example: More screen time leads to lower sleep quality.
Zero correlation (0): No relationship exists between the variables.
Strength tells you how closely related the variables are:
| Coefficient (r) | Strength |
|---|---|
| 0.00 – 0.29 | Weak |
| 0.30 – 0.49 | Moderate |
| 0.50 – 0.69 | Strong |
| 0.70 – 1.00 | Very strong |
One critical warning: Correlation does not equal causation. Just because two variables are related doesn’t mean one causes the other. For example, ice cream sales and drowning incidents are positively correlated, but that doesn’t mean ice cream causes drowning—both are caused by hot weather.
Pearson vs. Spearman: Which One Should You Use?
Choosing the wrong correlation test is one of the most common mistakes students make. Here’s how to decide.
Pearson Correlation (r)
Use Pearson when both of your variables are continuous (interval or ratio scale) and normally distributed, and the relationship between them is linear.
Examples of when to use Pearson:
Height vs. weight
Study hours vs. exam scores
Household income vs. monthly expenditure
Temperature vs. crop yield
Assumptions of Pearson:
Both variables are continuous
There is a linear relationship (check with a scatterplot)
No significant outliers exist
The data follows a bivariate normal distribution
Spearman Correlation (ρ or rho)
Use Spearman when your data is ordinal (ranked categories), not normally distributed, or the relationship is monotonic but not perfectly linear.
Examples of when to use Spearman:
Class rank vs. exam score
Customer satisfaction ranking (1-5) vs. spending amount
Education level (high school, bachelor’s, master’s) vs. income bracket
Any continuous data that violates normality assumptions
The key difference is that Pearson works with actual values, while Spearman works with ranked values. This makes Spearman more flexible and robust against outliers and non-normal distributions.
How to Perform Pearson Correlation in SPSS: Step-by-Step
Step 1: Prepare Your Data
Arrange your data in two columns in SPSS Data View. Each row represents one participant or observation. For example: Column A = “Study_Hours”, Column B = “Exam_Score”.
Step 2: Run the Analysis
Click Analyze → Correlate → Bivariate
Move both variables into the “Variables” box
Check Pearson under Correlation Coefficients
Select Two-tailed (standard for most research)
Check Flag significant correlations
Click OK
Step 3: Interpret the Output
SPSS will produce a correlation table. Look at the following:
Pearson Correlation: This is your r value (e.g., 0.78)
Sig. (2-tailed): This is your p-value (e.g., 0.001)
N: Your sample size
Decision rule: If p < 0.05, your correlation is statistically significant.
Example interpretation: “There was a strong, positive correlation between study hours and exam scores, r(28) = 0.78, p < .001.”
How to Perform Spearman Correlation in SPSS: Step-by-Step
Step 1: Prepare Your Data
Same data structure as Pearson. Spearman works with both ordinal and continuous data.
Step 2: Run the Analysis
Click Analyze → Correlate → Bivariate
Move both variables into the “Variables” box
Uncheck Pearson and check Spearman
Select Two-tailed
Click OK
Step 3: Interpret the Output
The output shows Spearman’s rho (ρ) instead of Pearson’s r.
Example interpretation: “A Spearman’s rank-order correlation was run to assess the relationship between class rank and exam score. There was a moderate, positive monotonic correlation, ρ(28) = 0.52, p = .003.”
How to Report Correlation Results in Your Thesis
Text Format (APA Style)
For Pearson: “A Pearson correlation coefficient was computed to assess the relationship between [Variable A] and [Variable B]. There was a [strength], [direction] correlation between the two variables, r(df) = [value], p = [value].”
For non-significant results: “No significant correlation was found between [Variable A] and [Variable B], r(28) = 0.12, p = .532.”
Including a Scatterplot
Always include a scatterplot with your correlation analysis. To create one in SPSS:
Click Graphs → Chart Builder
Choose Simple Scatter
Drag your variables to the X and Y axes
Click OK
Add a regression line by double-clicking the chart → Elements → Fit Line
Sample Complete Write-Up
*“Prior to analysis, assumptions of linearity and normality were assessed. A scatterplot revealed a linear relationship between study hours and exam scores. The Shapiro-Wilk test indicated data were normally distributed (p > .05). A Pearson correlation coefficient was then computed. There was a strong, positive correlation between study hours and exam scores, r(28) = 0.78, p < .001. This suggests that students who studied more hours tended to achieve higher exam scores.”*
Common Mistakes to Avoid
| Mistake | Why It’s Wrong |
|---|---|
| Confusing correlation with causation | Correlation does not imply one variable causes the other |
| Using Pearson with non-normal data | Violates assumptions and gives inaccurate results |
| Ignoring outliers | Outliers can artificially inflate or deflate your correlation |
| Forgetting to check for linearity | Pearson assumes a linear relationship |
| Reporting p-values without effect size | P-values don’t tell you about practical significance |
Conclusion
Correlation analysis is a powerful tool for exploring relationships between variables in your research. The key is knowing when to use Pearson versus Spearman. Remember: Pearson for normal, continuous, linear data; Spearman for ordinal, non-normal, or monotonic relationships. Always check your assumptions first, visualize your data with a scatterplot, and never confuse correlation with causation.
If you’re feeling overwhelmed by SPSS or unsure about your analysis, you don’t have to struggle alone. At Proposal Writers Kenya, our statistics experts can run your correlation analysis, interpret the output, and help you write up your results in proper APA format. Contact us today for a free quote and let us help you finish your thesis with confidence.