Survival models with a frailty term are presented as an extension of Cox’s proportional hazard model, in which a random effect is introduced in the hazard function in a multiplicative form with the aim of modeling the unobserved heterogeneity in the population. Candidates for the frailty distribution are assumed to be continuous and non-negative. However, this assumption may not be true in some situations. In this paper, we consider a discretely distributed frailty model that allows units with zero frailty, that is, it can be interpreted as having long-term survivors. We propose a new discrete frailty-induced survival model with a zero-modified power series family, which can be zero-inflated or zero-deflated depending on the parameter value. Parameter estimation was obtained using the maximum likelihood method, and the performance of the proposed models was performed by Monte Carlo simulation studies. Finally, the applicability of the proposed models was illustrated with a real melanoma cancer data set.
VaupelJWMantonKGStallardE.The impact of heterogeneity in individual frailty on the dynamics of mortality.Demography1979;
16: 439–454.
2.
CoxDR.Regression models and life-tables. J R Stat Soc: Ser B (Methodological)1972;
34: 187–202.
3.
WienkeA.Frailty models in survival analysis.
London:
Chapman and Hall/CRC, 2010.
4.
CalsavaraVFMilaniEABertolliE, et al.
Long-term frailty modeling using a non-proportional hazards model: application with a melanoma dataset.Stat Methods Med Res2020;
29: 2100–2118.
5.
VasquezJKRodriguesJBalakrishnanN.A useful variance decomposition for destructive Waring regression cure model with an application to HIV data. Commun Stat Theory Methods2020; 50: 1–12.
6.
CanchoVGMaceraMASuzukiAK, et al.
A new long-term survival model with dispersion induced by discrete frailty.Lifetime Data Anal2020;
26: 221–244.
7.
CaroniCCrowderMKimberA.Proportional hazards models with discrete frailty.Lifetime Data Anal2010;
16: 374–384.
8.
AtaNÖzelG.Survival functions for the frailty models based on the discrete compound Poisson process. J Stat Comput Simul2013;
83: 2105–2116.
9.
de SouzaDCanchoVGRodriguesJ, et al.
Bayesian cure rate models induced by frailty in survival analysis.Stat Methods Med Res2017;
26: 2011–2028.
10.
TsodikovADIbrahimJGYakovlevAY.Estimating cure rates from survival data: an alternative to two-component mixture models.J Am Stat Assoc2003;
98: 1063–1078.
11.
ConceiçãoKSLouzadaFAndradeM, et al.
Zero-modified power series distribution and its Hurdle distribution version. J Stat Comput Simul2017;
87: 1842–1862.
12.
Coordenação de Prevenção e Vigilância. Instituto Nacional de Cancer José Alencar Gomes da Silva. Estimativa 2018: Incidência de Cancer no Brasil. Coordenação de Prevenção e Vigilância—Rio de Janeiro, www1.inca.gov.br/estimativa/2018/ (2017, accessed 13 April 2021).
13.
ErvikMLamFFerlayJ, et al. Cancer Today. Lyon: International Agency for Research on Cancer, http://gco.iarc fr/today (2016, accessed 1 September 2020).
14.
DietzEBöhningD.On estimation of the Poisson parameter in zero-modified Poisson models. Comput Stat Data Anal2000;
34: 441–459.
15.
LambertD.Zero-inflated Poisson regression, with an application to defects in manufacturing. Technometrics1992;
34: 1–14.
16.
VieiraAHindeJPDemétrioCG.Zero-inflated proportion data models applied to a biological control assay. J Appl Stat2000;
27: 373–389.
17.
AgarwalDKGelfandAECitron-PoustyS.Zero-inflated models with application to spatial count data.Environ Ecol Stat2002;
9: 341–355.
18.
BarrySCWelshAH.Generalized additive modelling and zero inflated count data. Ecol Modell2002;
157: 179–188.
19.
RodriguesJ.Bayesian analysis of zero-inflated distributions. Commun Stat Theory Methods2003;
32: 281–289.
20.
LordDWashingtonSPIvanJN.Poisson, Poisson-gamma and zero-inflated regression models of motor vehicle crashes: balancing statistical fit and theory.Accid Anal Prev2005;
37: 35–46.
21.
OspinaRFerrariSL.A general class of zero-or-one inflated beta regression models. Comput Stat Data Anal2012;
56: 1609–1623.
22.
ConceiçãoKSAndradeMGLouzadaF.On the zero-modified Poisson model: Bayesian analysis and posterior divergence measure. Comput Stat2014;
29: 959–980.
23.
XavierDSantos-NetoMBourguignonM, et al. Zero-modified Poisson-Lindley distribution with applications in zero-inflated and zero-deflated count data. arXiv preprint arXiv:171204088, 2017.
24.
GuptaRC.Modified power series distribution and some of its applications. Sankhyā: Indian J Stat Ser B1974; 36: 288–298.
25.
ConsulPCFamoyeF.Lagrangian probability distributions. Berlin:Springer, 2006.
26.
CoxDROakesD.Analysis of survival data.
London:
Chapman and Hall, 1984.
27.
R Core Team. R: a language and environment for statistical computing.Vienna:
R Foundation for Statistical Computing, 2019. www.R-project.org/
28.
RochaRNadarajahSTomazellaV, et al.
A new class of defective models based on the Marshall-Olkin family of distributions for cure rate modeling. Comput Stat Data Anal2017;
107: 48–63.
29.
CalsavaraVRodriguesATomazellaV, et al.
Frailty models power variance function with cure fraction and latent risk factors negative binomial. Commun Stat Theory Methods2017;
46: 9763–9776.
30.
CalsavaraVFRodriguesASRochaR, et al.
Zero-adjusted defective regression models for modeling lifetime data. J Appl Stat2019;
46: 2434–2459.
31.
CalsavaraVFRodriguesASRochaR, et al.
Defective regression models for cure rate modeling with interval-censored data.Biometric J2019;
61: 841–859.
32.
LeãoJLeivaVSauloH, et al.
Incorporation of frailties into a cure rate regression model and its diagnostics and application to melanoma data.Stat Med2018;
37: 4421–4440.
33.
ScudilioJCalsavaraVRochaR, et al.
Defective models induced by gamma frailty term for survival data with cured fraction. J Appl Stat2019;
46: 487–507.
MallerRAZhouX.Survival analysis with long-term survivors.
New York:
John Wiley & Sons, 1996.
36.
GershenwaldJEScolyerRAHessKR, et al.
Melanoma staging: evidence-based changes in the American Joint Committee on Cancer eighth edition cancer staging manual. CA: A Cancer J Clin2017;
67: 472–492.
37.
BerksonJGageRP.Survival curve for cancer patients following treatment. J Am Stat Assoc1952;
47: 501–515.
38.
SabelMSGriffithKSondakVK, et al.
Predictors of nonsentinel lymph node positivity in patients with a positive sentinel node for melanoma.J Am Coll Surgeons2005;
201: 37–47.
39.
BalchCMThompsonJFGershenwaldJE, et al.
Age as a predictor of sentinel node metastasis among patients with localized melanoma: an inverse correlation of melanoma mortality and incidence of sentinel node metastasis among young and old patients. Ann Surg Oncol2014;
21: 1075–1081.
40.
BalchCMBuzaidACSoongSJ, et al.
Final version of the American Joint Committee on Cancer staging system for cutaneous melanoma.J Clin Oncol2001;
19: 3635–3648.
41.
BalchCMGershenwaldJESoongSJ, et al.
Final version of 2009 AJCC melanoma staging and classification.J Clin Oncol2009;
27: 6199.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
