From KIDSCREEN-10 to CHU9D: creating a unique mapping algorithm for application in economic evaluation

Table 3 Goodness-of-fit results from validation analysis

	Validation I			Validation II
	Pooled sample (N = 590)			Random sample I (N = 100)			Random sample II (N = 300)			Random sample III (N = 500)
	Mean utility	MAE	RMSE	Mean utility	MAE	RMSE	Mean utility	MAE	RMSE	Mean utility	MAE	RMSE
	(1)	(2)	(3)	(4)	(5)	(6)	(7)	(8)	(9)	(10)	(11)	(12)
Observed	0.8082	―	―	0.8265	―	―	0.8094	―	―	0.8102	―	―
Method 1: Ordinary least squares estimator
Model 1	0.8085	0.0982	0.1245	0.8166	0.0874	0.1091	0.8107	0.0938	0.1205	0.8111	0.0985	0.1248
Model 2	0.8088	0.0963^**	0.1209^*	0.8127	0.0845^**	0.1054^**	0.8112	0.0943	0.1187^*	0.8104	0.0947^**	0.1194^*
Method 2: Censored least absolute deviations estimator
Model 1	0.8202	0.0993	0.1268	0.8274	0.0867	0.1084	0.8211	0.0931^*	0.1209	0.8214	0.0977	0.1253
Model 2	0.8207	0.1006	0.1273	0.8378	0.0866	0.1097	0.8358	0.0946	0.1227	0.8344	0.0954	0.1232
Method 3: MM-estimator
Model 1	0.8133	0.0983	0.1253	0.8232	0.0865	0.1082	0.8164	0.0931^*	0.1208	0.8167	0.0977	0.1253
Model 2	0.8147	0.0962^*	0.1216^**	0.8201	0.0842^*	0.1053^*	0.8181	0.0937^**	0.1193^**	0.8168	0.0944^*	0.1200^**
Method 4: Generalised linear model
Model 1	0.8082	0.0977	0.1243	0.8149	0.0881	0.1097	0.8104	0.0940	0.1215	0.8108	0.0984	0.1252
Model 2	0.8085	0.0979	0.1226	0.8104	0.0920	0.1144	0.8085	0.0964	0.1206	0.8092	0.0967	0.1211

MAE – mean absolute error; RMSE – root mean squared error.
*denotes the smallest value in the column; **denotes the second smallest value in the column.

ISSN: 1477-7525