Table 3.
Goodness of fit results from validation analysis
| Validation method (3-fold) Pooled sample (N = 141) |
|||||
|---|---|---|---|---|---|
| Mean utility | RMSE | MAE | Ab diff < 0.03 |
Ab diff < 0.05 |
|
| Observed | 0.6619 | ||||
| Model 1 | |||||
| OLS | 0.6624 | 0.2220 | 0.1783 | 9.9 | 16.2 |
| GLM | 0.6153 | 0.2220 | 0.1916 | 3.5 | 9.2 |
| CLAD | 0.6925 | 0.2240 | 0.1730 | 12.7 | 19.7 |
| MFP | 0.7164 | 0.2288 | 0.1713 | 12.7 | 18.3 |
| MM | 0.7254 | 0.2309 | 0.1717 | 12.0 | 20.4 |
| BETA | 0.7246 | 0.2378 | 0.1775 | 10.6 | 16.2 |
| Model 2 | |||||
| OLS | 0.6696 | 0.2187 | 0.1738 | 8.5 | 16.2 |
| GLM | 0.6711 | 0.2197 | 0.1740 | 9.2 | 15.5 |
| CLAD | 0.7304 | 0.2316 | 0.1710 | 7.0 | 21.8 |
| MFP | 0.7224 | 0.2268 | 0.1684 | 11.3 | 16.9 |
| MM | 0.7313 | 0.2292 | 0.1688 | 11.3 | 16.9 |
| BETA | 0.7286 | 0.2355 | 0.1761 | 4.9 | 12.0 |
| Model 3 | |||||
| OLS | 0.6671 | 0.2153 | 0.1711 | 12.0 | 17.6 |
| GLM | 0.6671 | 0.2153 | 0.1711 | 12.0 | 17.6 |
| CLAD | 0.7173 | 0.2268 | 0.1700 | 11.3 | 14.8 |
| MFP | 0.7086 | 0.2204 | 0.1676 | 13.4 | 20.4 |
| MM | 0.7177 | 0.2229 | 0.1689 | 9.2 | 16.9 |
| BETA | 0.7347 | 0.2318 | 0.1740 | 11.3 | 16.9 |
| Indirect mapping | |||||
| OLOGIT | 0.6498 | 0.2353 | 0.1935 | 8.5 | 12.7 |
Dependant variable: EQ-5D-5 L utility score; Independent variables: Model 1 - MLHF total score; Model 2 – MLHF domain scores; Model 3 – MLHF item scores (Item 04, 17 and 21).
Abs diff. < 0.03 (0.05)% - proportion of predicted utilities whose absolute values deviate from the mean of the observed utility values by less than 0.03 (0.05); RMSE – Root Mean Square Error; MAE – Mean Absolute Error.
OLS - Ordinary least square; GLM - Generalized linear modelling; CLAD - Censored least absolute deviations; MFP - Multivariable fractional polynomials; MM - Robust MM estimator; BETA - Mixture beta regression model; OLOGIT ordered logit (indirect response mapping).