Is the value of a life or life-year saved context specific? Further evidence from a discrete choice experiment

Table 5 Parameter estimates for population-average model using robust regression with pweights

Predictor	β	SE	z	Sig.	β	SE	z	Sig.
	Lives saved				Life-years saved
Medical(B – A)				ns				ns
Cure(B – A)	-0.8476	0.110	-7.68	0.000	-0.8330	0.105	-7.93	0.000
AgeGrp_(B – A)^†			χ² = 130	0.000			χ² = 28.9	0.000
AgeGrp1(B – A)^†	1.2894	0.148	8.72	0.000	0.7448	0.144	5.17	0.000
AgeGrp2(B – A)^†	0.5936	0.138	4.30	0.000	0.3001	0.132	2.28	0.023
AgeGrp4(B – A)^†	-0.3810	0.110	-3.45	0.001	0.0187	0.130	0.14	0.886
Evidence(B – A)	0.6857	0.093	7.34	0.000	0.6572	0.093	7.05	0.000
Fault(B – A)	-0.5822	0.097	-5.98	0.000	-0.6560	0.104	-6.31	0.000
$Private(B – A)^	-0.0055	0.002	-2.49	0.013	-0.0077	0.002	-3.59	0.000
Effect(B – A)^‡	0.0338	0.004	8.43	0.000	0.0006	0.000	7.53	0.000
$Cost(B – A)^	-0.0060	0.001	-4.50	0.000	-0.0057	0.001	-4.22	0.000
HlthCard*Q	-0.0456	0.018	-2.52	0.012	-0.0454	0.018	-2.51	0.012
SIEFA_Econ*Q/1000	0.0693	0.022	3.15	0.002	0.0794	0.022	3.58	0.000
(Constant)	-0.3415	0.118	-2.89	0.004	-0.3995	0.117	-3.43	0.001
				N = 2329				N = 2329
				Wald χ² = 352.32, df = 11, p = 0.000				Wald χ² = 346.91, df = 11, p = 0.000
				Log-likelihood = -1234.69, Pseudo R² = 0.2350				Log-likelihood = -1239.33, Pseudo R² = 0.2321

^Dollar values expressed in AUD100,000s.
^†Reference category is 'working-age adults'. First, second and fourth dummies denote 'young children', 'young adults' and 'older-age retirees', respectively. Joint significance of dummies evaluated using Wald statistic on chi-square distribution.
^‡Effect(B – A) gives the incremental effectiveness of profile B compared to profile A defined in terms of terms of lives saved for the 'lives-saved' model and life-years saved for the 'life-years saved' model.

ISSN: 1478-7547