In this paper, we assume the competing causes to follow a Conway-Maxwell Poisson (COM-Poisson) distribution with lifetimes under interval censoring mechanism. COM-Poisson distribution comprises some discrete distributions such as geometric, Poisson and Bernoulli and the time-to-event distribution includes some lifetime distributions, namely, lognormal, gamma and Weibull. The flexibility of generalized gamma family of distributions is assessed by carrying out a generalized gamma simulation study using EM based algorithm for estimating the model parameters and their standard errors. A profile likelihood approach is applied to estimate the shape parameter of generalized gamma. Model discrimination is carried out based on likelihood ratio test, Akaike information criteria (AIC) and Bayesian information criteria (BIC), for varying sample sizes and cure fractions, within the generalized gamma family of distributions. A two-way modelling is carried out on a dataset, to illustrate the flexibility of the COM-Poisson family and the generalized gamma family of distributions to select the best fitted model.

cure rate models, COM-Poisson distributions, generalized gamma lifetimes, likelihood ratio test, Akaike information criteria, Bayesian information criteria.

Received: September 21, 2022; Revised: September 30, 2022; Accepted: October 15, 2022; Published: November 4, 2022

How to cite this article: Janani Amirtharaj and G. Vijayasree, Likelihood inference using EM based algorithm for COM-Poisson cure rate model with generalized gamma lifetimes under interval censoring, Advances and Applications in Statistics 82 (2022), 65-99. http://dx.doi.org/10.17654/0972361722081

This Open Access Article is Licensed under Creative Commons Attribution 4.0 International License

References:

[1] N. Balakrishnan and S. Pal, EM algorithm-based likelihood estimation for some cure rate models, J. Stat. Theory Prac. 6 (2012), 698-724.
[2] N. Balakrishnan and S. Pal, Lognormal lifetimes and likelihood-based inference for flexible cure rate models based on COM-Poisson family, Comput. Statist. Data Anal. 67 (2013), 41-67.
[3] N. Balakrishnan and S. Pal, Likelihood inference for flexible cure rate models with gamma lifetimes, Comm. Statist. Theory Methods 44 (2015), 4007-4048.
[4] N. Balakrishnan and S. Pal, An EM algorithm for the estimation of parameters of a flexible cure rate model with generalized gamma lifetimes and model discrimination using likelihood and information-based methods, Comput. Statist. 30 (2015), 151-189.
[5] N. Balakrishnan and S. Pal, Expectation maximization-based likelihood inference for flexible cure rate models with Weibull lifetimes, Stat. Methods Med. Res. 25(4) (2016), 1535-1563.
[6] N. Balakrishnan and Y. Peng, Generalized gamma frailty model, Stat. Med. 25(16) (2006), 2797-2816.
[7] J. Berkson and R. P. Gage, Survival cure for cancer patients following treatment, J. Amer. Statist. Assoc. 47 (1952), 501-515.
[8] J. W. Boag, Maximum likelihood estimates of the proportion of patients cured by cancer therapy, J. R. Stat. Soc. Ser. B 11 (1949), 15-53.
[9] R. W. Conway and W. L. Maxwell, A queuing model with state dependent services rates, The Journal of Industrial Engineering 12 (1961), 132-136.
[10] K. Davies, S. Pal and J. A. Siddiqua, Stochastic EM algorithm for generalized exponential cure rate model and an empirical study, J. Appl. Stat. 48(12) (2021), 2112-2135.
[11] V. T. Farewell, The use of mixture models for the analysis of survival data with long-term survivors, Biometrics 38 (1982), 1041-1046.
[12] Janani Amirtharaj and G. Vijayasree, COM-Poisson cure rate model with generalized exponential lifetimes under interval censoring: an EM-based approach, JP Journal of Biostatistics 21 (2022), 29-54.
[13] A. Y. C. Kuk and C. H. Chen, A mixture model combining logistic regression with proportional hazards regression, Biometrika 79 (1992), 531-541.
[14] T. A. Louis, Finding the observed information matrix when using the EM algorithm, J. Roy. Stat. Soc. Ser. B 44 (1982), 226-233.
[15] J. Majakwara and S. Pal, On some inferential issues for the destructive COM-Poisson-generalized gamma regression cure rate model, Comm. Statist. Simulation Comput. 48 (2019), 3118-3142.
[16] R. A. Maller and X. Zhou, Survival Analysis with Long-term Survivors, John Wiley & Sons, New York, 1996.
[17] G. J. McLachlan and T. Krishnan, The EM Algorithm and Extensions, 2nd ed., Hoboken, New Jersey, John Wiley & Sons, 2008.
[18] R. P. Murray, N. R. Anthonisen, J. E. Connett, R. A. Wise, P. G. Lindgren, P. G. Greene and M. A. Nides, Effects of multiple attempts to quit smoking and relapses to smoking on pulmonary function, Journal of Clinical Epidemiology 51 (1998), 1317-1326.
[19] S. Pal, A simplified stochastic EM algorithm for cure rate model with negative binomial competing risks: an application to breast cancer data, Stat. Med. 40(28) (2021), 6387-6409.
[20] S. Pal and N. Balakrishnan, An EM type estimation procedure for the destructive exponentially weighted Poisson regression cure model under generalized gamma lifetime, J. Stat. Comput. Simul. 87(6) (2016), 1107 1129.
[21] S. Pal and N. Balakrishnan, Likelihood inference for COM-Poisson cure rate model with interval- censored data and Weibull lifetimes, Stat. Methods Med. Res. 26(5) (2017), 2093- 2113.
[22] S. Pal and N. Balakrishnan, Likelihood inference based on EM algorithm for the destructive length-biased Poisson cure rate model with Weibull lifetime, Comm. Statist. Simulation Comput. 47(3) (2018), 644-660.
[23] S. Pal, S. Barui, K. Davies and N. Mishra, A stochastic version of the EM algorithm for mixture cure model with exponentiated Weibull family of lifetimes, J. Stat. Theory Prac. 16 (2022), Paper No. 48, 35 pp.
[24] S. Pal and S. Roy, A new non-linear conjugate gradient algorithm for destructive cure rate model and a simulation study: illustration with negative binomial competing risks, Comm. Statist. Simulation Comput. 47(10) (2020), 1-15.
[25] S. Pal and S. Roy, On the estimation of destructive cure rate model: a new study with exponentially weighted Poisson competing risks, Stat. Neerl. 75(3) (2021), 324-342.
[26] S. Pal, H. Yu, Z. D. Loucks and I. M. Harris, Illustration of the flexibility of generalized gamma distribution in modeling right censored survival data: analysis of two cancer datasets, Annals of Data Science 7(1) (2020), 77-90.
[27] Y. Peng and K. B. G. Dear, A nonparametric mixture model for cure rate estimation, Biometrics 56 (2000), 237-243.
[28] J. Rodrigues, M. de Castro, V. G. Cancho and N. Balakrishnan, COM-Poisson cure rate survival models and an application to a cutaneous melanoma data, J. Statist. Plann. Inference 139 (2009), 3605-3611.
[29] E. W. Stacy, A generalization of the gamma distribution, Ann. Math. Statist. 33(3) (1962), 1187-1192.
[30] J. Sun, The Statistical Analysis of Interval-censored Failure Time Data, New York, Springer, 2006.
[31] J. M. G. Taylor, Semi-parametric estimation in failure time mixture model, Biometrics 51(3) (1995), 899-907.
[32] J. Treszoks and S. Pal, A destructive shifted Poisson cure model for interval censored data and an efficient estimation algorithm, Comm. Statist. Simulation Comput. (2022) (to appear).
[33] P. Wang and S. Pal, A two-way flexible generalized gamma transformation cure rate model, Stat. Med. 41(13) (2022), 2427-2447.
[34] P. Wiangnak and S. Pal, Gamma lifetimes and associated inference for interval-censored cure rate model with COM-Poisson competing cause, Comm. Statist. Theory Methods 47(6) (2017), 1491-1509.
[35] A. Y. Yakovlev, Parametric versus nonparametric methods for estimating cure rates based on censored survival data, Stat. Med. 13 (1994), 983-985.