|
Size: 619
Comment:
|
Size: 640
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 1: | Line 1: |
| Line 11: | Line 10: |
| |||| 3 || 4 || | |||| 3 || 4 || |
| Line 13: | Line 13: |
| The change over time is the same (1) regardless of baseline so has no relationship with baseline score. The correlation between T1 and T2, on the other hand, is 1 because T2 is exactly 1 higher than T1 so is perfectly predicted by T1. | The change over time is the same (a difference of 1 unit) regardless of baseline so has no relationship with baseline score. The correlation between T1 and T2, on the other hand, is 1 because T2 is exactly 1 higher than T1 so is perfectly predicted by T1. |
How do I correlate change score with baseline?
To correlate change between two time points with baseline (at T1) we correlate the score at T1 with the difference in scores between T2 and T1. This is not the same as correlating T1 with T2.
To see this consider the following example
T1 |
T2 |
|
1 |
2 |
|
2 |
3 |
|
3 |
4 |
|
The change over time is the same (a difference of 1 unit) regardless of baseline so has no relationship with baseline score. The correlation between T1 and T2, on the other hand, is 1 because T2 is exactly 1 higher than T1 so is perfectly predicted by T1.