Review and implementation of cure models based on first hitting times for Wiener processes Jeremy Balka Anthony F. Desmond Email author Paul D. McNicholas Article

First Online: 04 January 2009 Received: 02 March 2008 Accepted: 19 November 2008 DOI :
10.1007/s10985-008-9108-y

Cite this article as: Balka, J., Desmond, A.F. & McNicholas, P.D. Lifetime Data Anal (2009) 15: 147. doi:10.1007/s10985-008-9108-y
Abstract The development of models and methods for cure rate estimation has recently burgeoned into an important subfield of survival analysis. Much of the literature focuses on the standard mixture model. Recently, process-based models have been suggested. We focus on several models based on first passage times for Wiener processes. Whitmore and others have studied these models in a variety of contexts. Lee and Whitmore (Stat Sci 21(4):501–513, 2006) give a comprehensive review of a variety of first hitting time models and briefly discuss their potential as cure rate models. In this paper, we study the Wiener process with negative drift as a possible cure rate model but the resulting defective inverse Gaussian model is found to provide a poor fit in some cases. Several possible modifications are then suggested, which improve the defective inverse Gaussian. These modifications include: the inverse Gaussian cure rate mixture model; a mixture of two inverse Gaussian models; incorporation of heterogeneity in the drift parameter; and the addition of a second absorbing barrier to the Wiener process, representing an immunity threshold. This class of process-based models is a useful alternative to the standard model and provides an improved fit compared to the standard model when applied to many of the datasets that we have studied. Implementation of this class of models is facilitated using expectation-maximization (EM) algorithms and variants thereof, including the gradient EM algorithm. Parameter estimates for each of these EM algorithms are given and the proposed models are applied to both real and simulated data, where they perform well.

Keywords Cure rate EM algorithm First hitting time Gradient EM algorithm Inverse Gaussian Mixture models Survival analysis Wiener process

References Aalen OO (1992) Modelling heterogeneity in survival analysis by the compound Poisson distribution. Ann Appl Probab 2: 951–972

MATH CrossRef MathSciNet Google Scholar Aalen OO (1994) Effects of frailty in survival analysis. Stat Methods Med Res 3: 227–243

CrossRef Google Scholar Aalen OO, Gjessing HK (2001) Understanding the shape of the hazard rate: a process point of view. Stat Sci 16: 1–22

MATH MathSciNet Google Scholar Achcar J, Araujo Pereira G (1999) Mixture models for type II censored survival data in the presence of covariates. Comput Stat 14: 233–250

MATH CrossRef Google Scholar Berkson J, Gage RP (1952) Survival curve for cancer patients following treatment. J Am Stat Assoc 47: 501–515

CrossRef Google Scholar Boag JW (1949) Maximum likelihood estimates of the proportion of patients cured by cancer therapy. J R Stat Soc B 11: 15–34

MATH Google Scholar Cantor AB, Shuster JJ (1992) Parametric versus non-parametric methods for estimating cure rates based on censored survival data. Stat Med 11: 931–937

CrossRef Google Scholar Chen M-H, Ibrahim JG, Sinha D (1999) A new Bayesian model for survival data with a surviving fraction. J Am Stat Assoc 94: 909–919

MATH CrossRef MathSciNet Google Scholar Chhikara RS, Folks JL (1978) The inverse Gaussian distribution and its statistical application-a review. J R Stat Soc B 40: 263–289

MATH MathSciNet Google Scholar Cox DR (1972) Regression models and life-tables (with discussion). J R Stat Soc B 34: 187–220

MATH Google Scholar Cox DR (1999) Some remarks on failure-times, surrogate markers, degradation, wear, and the quality of life. Lifetime Data Anal 5: 307–314

MATH CrossRef MathSciNet Google Scholar Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm (with discussion). J R Stat Soc B 39: 1–38

MATH MathSciNet Google Scholar Desmond AF, Chapman GR (1992) Likelihood inference for inverse Gaussian mixtures. Technical report, Department of Mathematics and Statistics, University of Guelph, Ontario, Canada

Desmond AF, Chapman GR (1993) Modelling task completion data with inverse Gaussian mixtures. Appl Stat 42(4): 603–613

CrossRef Google Scholar Desmond AF, Yang ZL (2006) Score tests of goodness-of-fit for the inverse Gaussian distribution. Technical report, Department of Mathematics and Statistics, University of Guelph

Duchateau L, Janssen P (2008) The frailty model. Springer, New York

MATH Google Scholar Farewell VT (1982) The use of mixture models for the analysis of survival data with long-term survivors. Biometrics 38: 1041–1046

CrossRef Google Scholar Farewell VT (1986) Mixture models in survival analysis: are they worth the risk. Can J Stat 14: 257–262

CrossRef MathSciNet Google Scholar Feller W (1986) An introduction to probability theory and its applications. Wiley, New York

Google Scholar Gieser PW, Chang MN, Rao PV, Shuster JJ, Pullen J (1998) Modelling cure rates using the Gompertz model with covariate information. Stat Med 17: 831–839

CrossRef Google Scholar Haybittle JL (1959) The estimation of the proportion of patients cured after treatment for cancer of the breast. Br J Radiol 32: 725–733

Google Scholar Ichida J, Wassell J, Keller M, Ayers L (1993) Evaluation of protocol change in burn-care management using the Cox proportional hazards model with time-dependent covariates. Stat Med 12: 301–310

CrossRef Google Scholar Kalbfleisch JD, Prentice RL (2002) The statistical analysis of failure time data, 2nd edn. Wiley, New York

Google Scholar Knight F (1981) Essentials of Brownian motion and diffusion, math surveys and monographs no. 18. Amer Math Soc, Providence, Rhode Island

Kuk AYC, Chen CH (1992) A mixture model combining logistic regression with proportional hazards regression. Biometrika 79: 531–541

MATH CrossRef Google Scholar Kuo L, Peng F (1995) A mixture-model approach to the analysis of survival data. Technical report 95–31, Department of Statistics, University of Connecticut

Lancaster T (1972) A stochastic model for the duration of a strike. J R Stat Soc A 135: 257–271

CrossRef Google Scholar Lange K (1995a) A gradient algorithm locally equivalent to the EM algorithm. J R Stat Soc B 57: 425–437

MATH Google Scholar Lange K (1995b) A quasi-Newton acceleration of the EM algorithm. Stat Sin 5: 1–18

MATH Google Scholar Lawless JF (2003) Statistical models and methods for lifetime data. 2nd edn. Wiley, New York

Google Scholar Lee M-LT, Whitmore GA (2004) First hitting time models for lifetime data. In: Balakrishnan N, Rao CR(eds) Handbook of statistics, vol 23. Elsevier, Amsterdam, pp 537–543

Google Scholar Lee M-LT, Whitmore GA (2006) Threshold regression for survival analysis: modeling event times by a stochastic process reaching a boundary. Stat Sci 21(4): 501–513

MATH CrossRef MathSciNet Google Scholar Lesosky M, Horrocks J (2004) Generating random variables from the inverse Gaussian and first-passage-two-barrier distributions. Technical report, Department of Mathematics and Statistics, University of Guelph

Longini IN, Halloran ME (1996) A frailty mixture model for estimating vaccine efficacy. Appl Stat 45: 165–173

MATH CrossRef Google Scholar Maller RA, Zhou X (1996) Survival analysis with long-term survivors. Wiley, West Sussex

MATH Google Scholar McLachlan GJ, Krishnan T (2008) The EM algorithm and extensions, 2nd edn. Wiley, New York

CrossRef Google Scholar Pelsser A (2000) Pricing double barrier options using laplace transforms. Finance and Stochastics 4: 95–104

MATH CrossRef MathSciNet Google Scholar Peng Y, Dear KBG (2000) A nonparametric mixture model for cure rate estimation. Biometrics 56: 237–243

MATH CrossRef Google Scholar Peng Y, Dear KBG, Denham JW (1998) A generalized F mixture model for cure rate estimation. Stat Med 17: 813–830

CrossRef Google Scholar Rai SN, Matthews DE (1995) Improving the EM algorithm. Biometrics 49: 587–591

CrossRef MathSciNet Google Scholar Schrödinger E (1915) Zur theorie der fall-und steigversuche an teilchen mit brownscher bewegung. Phys Ze 16: 289–295

Google Scholar Sy JP, Taylor JMG (2000) Estimation in a Cox proportional hazards cure model. Biometrics 56: 227–236

MATH CrossRef MathSciNet Google Scholar Taylor JMG (1995) Semi-parametric estimation in failure time mixture models. Biometrics 51: 899–907

MATH CrossRef Google Scholar Tweedie MCK (1945) Inverse statistical variates. Nature 155: 453

MATH CrossRef MathSciNet Google Scholar Whitmore GA (1979) An inverse Gaussian model for labour turnover. J R Stat Soc A 142: 468–478

CrossRef Google Scholar Whitmore GA (1986) Normal-gamma mixtures of inverse Gaussian distributions. Scand J Stat 13: 211–220

MATH MathSciNet Google Scholar Whitmore GA, Su Y (2007) Modeling low birth weights using threshold regression: results for U.S. birth data. Lifetime Data Anal 13: 161–190

CrossRef MathSciNet MATH Google Scholar Whitmore GA, Crowder MJ, Lawless JF (1998) Failure inference from a marker process based on a bivariate Wiener model. Lifetime Data Anal 4: 229–251

MATH CrossRef Google Scholar Yakovlev AY, Asselain B, Bardou VJ, Fourquet A, Hoang R, Rochefediere A, Tsodikov AD (1993) A simple stochastic model of tumor recurrence and its applications to data on premenopausal breast cancer. In: Asselain CDCLJPMB, Boniface M, Tranchefort J (eds) Biometrie et Analyse de Donnees Spatio-Temporelles, pp 66–82

© Springer Science+Business Media, LLC 2009

Authors and Affiliations Jeremy Balka Anthony F. Desmond Email author Paul D. McNicholas 1. Department of Mathematics & Statistics University of Guelph Guelph Canada