Partial Correlation Analysis using SPSS
What is Partial Correlation?
- Bivariate correlation provide correlation between two variables, the resulting value might be effected by other variables in the study, you might need to control the effect of another variable on your correlation.
- if you want to learn more about Bivariate Correlation, Click Here
- Partial Correlation allows you to control the effect of an additional variable. By statistically removing the influence of this variable, you can get a clearer and more accurate indication of the relationship between your two variables.
- Now what happens if you do not control the variable, it may be so that the correlation between two variables is due to another variable, that overestimates the correlation between two variables, controlling the variable may lower the correlation between the two variables of interest.
Example of Partial Correlation
Investigate the relationship between Servant Leadership (SL) and Life Satisfaction (LS).
H1: There is a significant relationship between servant leadership and life satisfaction.
- Two continuous variables (In this case, Servant Leadership and Life Satisfaction)
- Controlling Variable (Categorical or Continuous) – Experience in this example.
How to Run Partial Correlation
- Choose Analyze → Correlate → Partial
- The resulting dialog box is shown in Figure.
- Choose the variables for which the correlation is to be studied from the left-hand side box and move them to the right-hand side box labeled Variables. Once any two variables are transferred to the variables box, the OK button becomes active. We can transfer more than two variables, but for now we will stick to only two.
- Now Select Experience from the left-hand box and click arrow before the Controlling For box and insert the variable. The resulting dialog box should look like one in the Figure.
- Click on button labeled Options, the following dialog box (see Figure) is displayed, Check Zero-order correlation.
- Click Continue
- There are some default selections at the bottom of the window; these can be changed by clicking on the appropriate boxes. For our purpose, we will stick to Two-Tailed in Tests of Significance. Keep the Display actual significance level.
- Press OK
Output Partial Correlation
Here is the output of Partial Correlation Analysis in SPSS
Interpretation of Partial Correlation Matrix
The output provides you with a table made up of two sections:
In the top half of the table is the normal Pearson product-moment correlation matrix between your two variables of interest (SL and LS), not controlling for your other variable. In this case, the correlation is .526. The word ‘none’ in the left-hand column indicates that no control variable is in operation.
The bottom half of the table repeats the same set of correlation analyses, but this time controlling for (taking out) the effects of your control variable (Experience). The variable we are controlling for in the analysis (for example, Experience in our case) is shown in the left-hand side. In this case, the new partial correlation is .511. You should compare these two sets of correlation coefficients to see whether controlling for the additional variable had any impact on the relationship between your two variables. In this example, there was only a small decrease in the strength of the correlation (from .526 to .511). This suggests that the observed relationship between SL and LS is not due merely to the influence of Experience. This means that even if we control for the Experience, the Servant Leadership (SL) will still be significantly related to the Life Satisfaction (LS).
Sample Interpretation Partial Correlation?
Reporting Partial Correlation
The relationship between Servant Leadership (SL) and Life Satisfaction (LS) was explored using Partial correlation, while controlling for experience. There was a moderate positive partial correlation between SL and LS, controlling for experience, r = .511, n = 218, p < .001, with increase in SL significantly related to higher LS. An inspection of the zero-order correlation (r = .526) suggested that controlling for experience had very little effect on the strength of the relationship between these two variables.
To understand how to run Partial Correlation in SPSS, please watch the video