Skip to main content

Table 6 Model performance of three regression methods for mapping the PHQ-8 to the SF-6D utility scores

From: Mapping the PHQ-8 to EQ-5D, HUI3 and SF6D in patients with depression

No Mapping method Number of components and truncation Specification ME MAE RMSE MAE rank RMSE rank ARV
1 BETAMIX M1a 1 component without truncation Probability mass at full health 0.0008 0.0587 0.0746 10 9 9.2
2 BETAMIX M1b 2 components without truncation Probability mass at full health 0.0060 0.0575 0.0749 9 10 9.2
3 BETAMIX M1c 2 components with truncation Probability mass at full health N/A N/A N/A N/A N/A N/A
4 BETAMIX M1d 2 components with truncation Probability mass at full health and truncation point N/A N/A N/A N/A N/A N/A
5 BETAMIX M2a 1 component without truncation Probability mass at full health 0.0013 0.0539 0.0695 6 6 6
6 BETAMIX M2b 2 components without truncation Probability mass at full health 0.0055 0.0527 0.0693 2 5 3.5
7 BETAMIX M2c 2 components with truncation Probability mass at full health N/A N/A N/A N/A N/A N/A
8 BETAMIX M2d 2 components with truncation Probability mass at full health and truncation point N/A N/A N/A N/A N/A N/A
9 BETAMIX M3a 1 component without truncation Probability mass at full health 0.0020 0.0533 0.0683 5 2 3.5
10 BETAMIX M3b 2 components without truncation Probability mass at full health 0.0057 0.0519 0.0683 1 1 1
11 BETAMIX M3c 2 components with truncation Probability mass at full health N/A N/A N/A N/A N/A N/A
12 BETAMIX M3d 2 components with truncation Probability mass at full health and truncation point N/A N/A N/A N/A N/A N/A
13 OLS M1    0.0000 0.0587 0.0754 11 11 11
14 OLS M2    0.0000 0.0545 0.0710 7 7 7
15 OLS M3    0.0000 0.0532 0.0686 3 3 3
16 TOBIT M1    0.0000 0.0587 0.0754 12 12 12
17 TOBIT M2    0.0000 0.0545 0.0710 8 8 8
18 TOBIT M3    0.0000 0.0532 0.0686 4 4 4
  1. N/A Not available due to no values at the upper boundary of full health