A Solution to the Problem of Monotone Likelihood in Cox Regression

The phenomenon of monotone likelihood is observed in the fitting process of a Cox model if the likelihood converges to a finite value while at least one parameter estimate diverges to +/- infinity. Monotone likelihood primarily occurs in small samples with substantial censoring of survival times and several highly predictive covariates. Previous options to deal with monotone likelihood have been unsatisfactory. The solution we suggest is an adaptation of a procedure by Firth (1993, Biometrika 80, 27-38) originally developed to reduce the bias of maximum likelihood estimates. This procedure produces finite parameter estimates by means of penalized maximum likelihood estimation. Corresponding Wald-type tests and confidence intervals are available, but it is shown that penalized likelihood ratio tests and profile penalized likelihood confidence intervals are often preferable. An empirical study of the suggested procedures confirms satisfactory performance of both estimation and inference. The advantage of the procedure over previous options of analysis is finally exemplified in the analysis of a breast cancer study.

[1]  P. McCullagh,et al.  Bias Correction in Generalized Linear Models , 1991 .

[2]  D. Firth.  Generalized Linear Models and Jeffreys Priors: An Iterative Weighted Least-Squares Approach , 1992 .

[3]  D. Cox,et al.  Analysis of Survival Data. , 1985 .

[4]  R. Schaefer.  Bias correction in maximum likelihood logistic regression. , 1985, Statistics in medicine.

[5]  D. Collett.  Modelling survival data , 1994 .

[6]  David R. Cox,et al.  Regression models and life tables (with discussion , 1972 .

[7]  Mark E. Johnson,et al.  The Incidence of Monotone Likelihood in the Cox Model , 1981 .

[8]  H. Tolley,et al.  Covariate analysis of survival data: a small-sample study of Cox's model. , 1982, Biometrics.

[9]  C. Kainz,et al.  Prognostic value of cathepsin D expression and association with histomorphological subtypes in breast cancer. , 1998, British Journal of Cancer.

[10]  D. Cox.  Regression Models and Life-Tables , 1972 .

[11]  R. Musgrave,et al.  Long-term outcome and patterns of failure in patients with advanced head and neck cancer , 2011, Radiation oncology.

[12]  You-Gan Wang,et al.  Bias Reduction using Stochastic Approximation , 1998 .

[13]  James F. Watkins,et al.  Analysing Survival Data from Clinical Trials and Observational Studies. , 1995 .

[14]  Francisco Cribari-Neto,et al.  On bias reduction in exponential and non-exponential family regression models , 1998 .

[15]  T. Loughin,et al.  On the Bootstrap and Monotone Likelihood in the Cox Proportional Hazards Regression Model , 1998, Lifetime data analysis.

[16]  M. Jacobsen.  Existence and unicity of MLEs in discrete exponential family distributions , 1989 .

[17]  David Collett.  Modelling Survival Data in Medical Research , 1994 .

[18]  M. Schemper,et al.  The application of Firth's procedure to Cox and logistic regression , 2001 .

[19]  P. McCullagh,et al.  Generalized Linear Models , 1984 .

[20]  David Firth,et al.  Bias reduction, the Jeffreys prior and GLIM , 1992 .

[21]  D. Firth.  Bias reduction of maximum likelihood estimates , 1993 .