A local likelihood proportional hazards model for interval censored data
Statistics in MedicinePublished 21 December 2001
Rebecca A. Betensky, Jane C. Lindsey, Louise Ryan, M. P. Wand
Citations74
SJR quartileQ1
SJR score1.27
SNIP1.33
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The use of local likelihood methods to fit proportional hazards regression models to right and interval censored data and extends the modified EM algorithm suggested by Betensky, Lindsey, Ryan and Wand for estimation.
Abstract
We discuss the use of local likelihood methods to fit proportional hazards regression models to right and interval censored data. The assumed model allows for an arbitrary, smoothed baseline hazard on which a vector of covariates operates in a proportional manner, and thus produces an interpretable baseline hazard function along with estimates of global covariate effects. For estimation, we extend the modified EM algorithm suggested by Betensky, Lindsey, Ryan and Wand. We illustrate the method with data on times to deterioration of breast cosmeses and HIV-1 infection rates among haemophiliacs.
Keywords
Mathematics
Journal of the Royal Statistical Society Series B (Statistical Methodology)Regression Models and Life-Tables
39,259 Citations1972D. R. Cox
Journal of the Royal Statistical Society Series B (Statistical Methodology)The Empirical Distribution Function with Arbitrarily Grouped, Censored and Truncated Data
1,814 Citations1976Bruce W. Turnbull
BiometricsA Proportional Hazards Model for Interval-Censored Failure Time Data
665 Citations1986Dianne M. Finkelstein
The method developed is used to analyze data from an animal tumorigenicity study and also a clinical trial, and results given for testing the hypothesis of a zero regression coefficient lead to a generalization of the log-rank test for comparison of several survival curves.
TechnometricsTheory and Applications of Hazard Plotting for Censored Failure Data
562 Citations2000Wayne Nelson
Journal of the American Statistical AssociationLocal Likelihood Estimation
520 Citations1987Robert Tibshirani, Trevor Hastie
TechnometricsTheory and Applications of Hazard Plotting for Censored Failure Data
497 Citations1972Wayne Nelson
The Annals of StatisticsEfficient estimation for the proportional hazards model with interval censoring
436 Citations1996Jian Huang
Statistics in MedicineMethods for interval-censored data
363 Citations1998Jane C. Lindsey, Louise Ryan
This tutorial is to illustrate and compare available methods which correctly treat the data as being interval-censored and to allow those familiar with the application of standard survival analysis techniques the option of applying appropriate methods when presented with interval- censored data.
Journal of the Royal Statistical Society Series C (Applied Statistics)Experimental Survival Curves for Interval-Censored Data
340 Citations1973Richard Peto
A method is given for calculating from interval‐ censored data an estimate of the c.d.f. which is analogous to the estimate derivable from right‐censored data by the life‐table technique.
The Annals of StatisticsLocal likelihood density estimation
305 Citations1996Clive Loader
In this paper an extension of local likelihood methods to density estimation is discussed, and comparison with other methods of density estimation presented.
BiometrikaMaximum likelihood for interval censored data: Consistency and computation
191 Citations1994Robert Gentleman, Charles J. Geyer
Journal of Computational and Graphical StatisticsLogspline Density Estimation for Censored Data
168 Citations1992Charles Kooperberg, Charles J. Stone
BiometricsHazard Function Estimation Using B-Splines
164 Citations1995Philip S. Rosenberg
A flexible parametric procedure is given to model the hazard function as a linear combination of cubic B-splines and to obtain maximum likelihood estimates from censored survival data, which yields smooth estimates of the hazard and survivorship functions that are intermediate in structure between strongly parametric and non-parametric models.
BiometricsCensoring in an Epidemic with an Application to Hemophilia-Associated AIDS
160 Citations1989Ron Brookmeyer, James J. Goedert
A two-stage parametric regression model is proposed for the analysis of cohort studies during an epidemic in which the exact times of infection cannot be ascertained and it was found that hemophiliacs with severe Type A hemophilia were at highest risk of infection, and therisk of infection increased sharply in the early 1980s.
AIDSEffect of age at seroconversion on the natural AIDS incubation distribution
158 Citations1994Philip S. Rosenberg, James J. Goedert
The increasing risk with age was similar in hemophiliacs and homosexual men, suggesting that age is an endogenous host factor and can be incorporated into newly developed backcalculation models to estimate HIV infection incidence by age group from age-specific AIDS surveillance data.
Statistics in MedicineA NON-PARAMETRIC TEST FOR INTERVAL-CENSORED FAILURE TIME DATA WITH APPLICATION TO AIDS STUDIES
155 Citations1996Jianguo Sun
This article proposes a non-parametric test, a generalization of the usual logrank test for right-censored failure time data, for situations in which the underlying failure time is a discrete variable or the observed times correspond with a discrete scale.
The Annals of StatisticsLocal likelihood and local partial likelihood in hazard regression
143 Citations1997Jianqing Fan, Irène Gijbels +1 more
Journal of the American Statistical AssociationRegression Splines in the Cox Model with Application to Covariate Effects in Liver Disease
137 Citations1990Lynn A. Sleeper, David P. Harrington
A survival model based on data from a clinical trial of primary biliary cirrhosis is developed using regression splines, and the resulting log hazard ratio estimates are compared with those from nonparametric methods.
Statistical ScienceInference Based on Estimating Functions in the Presence of Nuisance Parameters
131 Citations1995Kung‐Yee Liang, Scott L. Zeger
BiometricsA Proportional Hazards Model for Arbitrarily Censored and Truncated Data
115 Citations1996Ahmadou Alioum, Daniel Commenges
This paper presents a detailed correction of Turnbull's method and an extension to the regression analysis: a method of fitting the proportional hazards model for arbitrarily censored and truncated data is developed and allows partial testing for zero regression coefficients.
BiometrikaRank-based inference in the proportional hazards model for interval censored data
109 Citations1996Glen A. Satten
BiometricsHazard Regression with Interval-Censored Data
93 Citations1997Charles Kooperberg, Douglas B. Clarkson
The HARE methodology is extended to accommodate interval- censored data, time-dependent covariates, and cubic splines, and the presence of interval-censored data means that the log-likelihood function may no longer be concave, presenting additional numerical challenges.
BiometricsSome Diagnostic Methods for Cox Regression Models Through Hazard Smoothing
74 Citations1990Robert J. Gray
In this paper some graphical methods are proposed for evaluating the fit of Cox regression models in survival analysis, applied to data taken from a clinical trial of adjuvant therapy for breast cancer.
BiometricsA Markov Chain Monte Carlo EM Algorithm for Analyzing Interval-Censored Data under the Cox Proportional Hazards Model
69 Citations1998William B. Goggins, Dianne M. Finkelstein +2 more
This paper proposes a Monte Carlo EM algorithm for fitting the proportional hazards model for interval-censored failure-time data and indicates that this method produced more precise and unbiased estimates than methods of right and midpoint imputation.
Journal of the American Statistical AssociationInference Based on Imputed Failure Times for the Proportional Hazards Model with Interval-Censored Data
65 Citations1998Glen A. Satten, Somnath Datta +1 more
Journal of Computational and Graphical StatisticsLogspline Density Estimation for Censored Data
63 Citations1992Charles Kooperberg, Charles J. Stone
BiometricsLocal EM Estimation of the Hazard Function for Interval‐Censored Data
48 Citations1999Rebecca A. Betensky, Jane C. Lindsey +2 more
A smooth hazard estimator for interval-censored survival data using the method of local likelihood is proposed, which is more descriptive than traditional empirical estimates in regions of concentrated information and takes on a parametric flavor in areas of sparse information.
Statistics in MedicineINTERVAL CENSORED SURVIVAL DATA: A GENERALIZED LINEAR MODELLING APPROACH
38 Citations1996Paddy Farrington
Three types of models are discussed: additive and multiplicative hazard models with piecewise constant baseline hazard, and a proportional hazards model with discrete baseline survivor function that may be fitted in the statistical package GLIM.
Journal of Computational and Graphical StatisticsHazard Rate Regression Using Ordinary Nonparametric Regression Smoothers
32 Citations1996Malcolm H. Ray
Sociological Methods & ResearchAssessing Bias and Fit of Global and Local Hazard Models
26 Citations1991Lawrence Wu, Nancy Brandon Tuma
This article assesses the bias and fit of a hazard rate model by comparing predicted and nonparametric estimates of survivor probabilities, and suggests that a nonproportional local Gompertz model performs better than other models examined.
BiometricsEfficiencies of Experimental Designs for an Illness-Death Model
24 Citations1984Ørnulf Borgan, Knut Liestøl +1 more
The discussion is based on the 'semiparametric' assumption of piecewise-constant intensities and simple survival experiments are shown to have very low efficiency, serial sacrifice experiments to be moderately efficient, and periodic diagnosis to be almost as efficient as complete observation.
Sociological MethodologyLocal Hazard Models
19 Citations1990Lawrence Wu, Nancy Brandon Tuma
A class of local hazard models that maintain parametric assumptions locally rather than globally are introduced, which allow estimation of a flexible baseline hazard rate and nonproportional covariate effects and provide interesting substantive insights into the process of first marriage.
BiometricsAn Illness-Death Process with Time-Dependent Covariates
14 Citations1989Y. Chiang, Robert J. Hardy +2 more
This method provides an analytical approach with which the effectiveness of the treatment can be compared between the placebo and propranolol treatment groups with respect to fatal and nonfatal events simultaneously.