A new cure model that corrects for increased risk of non-cancer death: analysis of reliability and robustness, and application to real-life data

Table 6 Performance indicators of Model(1) in presence of data generated with α randomly assigned among patients

	α range	AB						SD						CVD
	α range	α	π	λ	γ	β	δ	α	π	λ	γ	β	δ	α	π	λ	γ	β	δ
BREAST^a	0.832–1.664	− 0.024	− 0.006	− 0.001	0.003	− 0.019	− 0.001	0.091	0.036	0.010	0.044	0.165	0.132	95%	94%	94%	94%	95%	95%
	0.659–1.978	− 0.066	− 0.013	− 0.002	− 0.004	− 0.042	0.022	0.089	0.036	0.010	0.044	0.160	0.126	88%	96%	94%	95%	95%	95%
	0.555–2.218	−0.106	− 0.019	− 0.002	− 0.003	− 0.039	0.019	0.088	0.036	0.010	0.043	0.155	0.120	77%	95%	91%	95%	94%	96%
LUNG^b	1.386–2.773	−0.042	0.002	−0.009	− 0.001	0.002	0.003	0.204	0.004	0.014	0.015	0.064	0.022	95%	93%	89%	96%	95%	96%
	1.099–3.296	−0.108	0.001	− 0.010	− 0.002	− 0.002	0.003	0.201	0.004	0.014	0.015	0.064	0.022	91%	95%	89%	96%	96%	96%
	0.924–3.697	−0.165	0.001	−0.010	− 0.002	− 0.006	0.003	0.196	0.004	0.014	0.015	0.063	0.022	86%	96%	89%	95%	96%	96%

Absolute Bias (AB) = Mean(estimates - true value); Standard Deviation (SD) = standard deviation over the set of 1000 estimates; Coverage (CVR) = the proportion of the time that the estimated 95% confidence intervals contained the true value
Estimated over 1000 simulation runs; Sample size 10,000; follow-up 15 years
^aTrue values: α = 1.2, π₆₀ = 0.7, λ = 0.1, γ = 1.1, β = − 0.15 and δ = 0
^bTrue values: α = 2, π₆₀ = 0.1, λ = 0.9, γ = 0.8, β = − 0.75 and δ = − 0.3

ISSN: 1471-2288