Partial correlation
Command: | Statistics Correlation Partial correlation |
Description
Use Partial correlation when you suspect the relationship between 2 variables to be influenced by other variables. The partial correlation coefficient is said to be adjusted or corrected for the influence by the different covariates.
Required input
Variable Y - Variable X
Select the 2 variables of interest.
Covariates
The variables that you suspect to influence the relationship between the X and Y variables.
Select
(Optionally) enter a filter in order to include only a selected subgroup of cases in the statistical analysis.
Options
You can select a Logarithmic transformation for one or both variables.
Results
Variable Y | GRADE_A |
---|---|
Variable X | ATP |
Covariates |
---|
CONCENTRATION |
MORPHOLOGY |
Sample size | 46 |
---|---|
Correlation coefficient r | 0.1805 |
Significance level | P=0.2410 |
The results window for Partial correlation displays:
- Sample size: the number of (selected) data pairs
- Correlation coefficient: Partial correlation coefficient, with P-value
Literature
- Altman DG (1991) Practical statistics for medical research. London: Chapman and Hall.