A semiparametric inverse-Gaussian model and inference for survival data with a cured proportion

被引:9
|
作者
Choi, Sangbum [1 ]
Huang, Xuelin [2 ]
Cormier, Janice N. [3 ]
Doksum, Kjell A. [4 ]
机构
[1] Univ Texas Hlth Sci Ctr Houston, Div Clin & Translat Sci, Dept Internal Med, Houston, TX 77030 USA
[2] Univ Texas MD Anderson Canc Ctr, Dept Biostat, Houston, TX 77030 USA
[3] Univ Texas MD Anderson Canc Ctr, Dept Surg Oncol, Houston, TX 77030 USA
[4] Univ Wisconsin, Dept Stat, Madison, WI 53706 USA
关键词
Degradation model; first-hitting-time; improper distribution; nonparametric likelihood; threshold regression; transformation model; Wiener process; TRANSFORMATION MODELS; DEGRADATION MODELS; CHECKING;
D O I
10.1002/cjs.11226
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
This work focuses on a semiparametric analysis of a cure rate modelling approach based on a latent failure process. In clinical and epidemiological studies, a Wiener process with drift may represent a patient's health status and a clinical endpoint occurs when the process first reaches an adverse threshold state. The first-hitting-time then follows an inverse-Gaussian distribution. On the basis of the improper inverse-Gaussian distribution, we consider a process-based lifetime model that allows for a positive probability of no event taking place in finite time. Model flexibility is achieved by leaving a transformed time measure for disease progression completely unspecified, and regression structures are incorporated into the model by taking the acceleration factor and the threshold parameter as functions of the covariates. When applied to experiments with a cure fraction, this model is compatible with classical two-mixture or promotion-time cure rate models. We develop an asymptotically efficient likelihood-based estimation and inference procedure and derive the large-sample properties of the estimators. Simulation studies demonstrate that the proposed method performs well in finite samples. A case study of stage-III soft tissue sarcoma data is used as an illustration. The Canadian Journal of Statistics 42: 635-649; 2014 (c) 2014 Statistical Society of Canada Resume Les auteurs presentent une approche semi-parametrique pour un modele de taux de guerison base sur un processus latent de defaillance. Dans le cadre d'etudes cliniques ou epidemiologiques, un processus de Wiener avec derive peut representer l'etat de sante d'un patient, et un evenement clinique survient lorsque le processus atteint le seuil critique associe a un etat defavorable. Le premier temps de passage suit alors une loi gaussienne inverse. Sur la base de la loi gaussienne inverse impropre, les auteurs considerent un modele de duree de vie base sur un processus oU la probabilite qu'aucun evenement ne se produise dans un temps fini peut etre positive. La flexibilite du modele est obtenue en evitant de specifier la transformation appliquee au temps de progression de la maladie, et en exprimant le facteur d'acceleration et le seuil comme des fonctions des covariables, incorporant ainsi des structures de regression dans le modele. Lorsqu'il est utilise pour l'analyse de donnees comportant une fraction de guerison, ce modele est compatible avec les modeles classiques de taux de guerison a deux melanges ou a temps de promotion. Les auteurs developpent une procedure d'estimation et d'inference basee sur la vraisemblance dont ils derivent les proprietes asymptotiques, y compris l'efficacite asymptotique. Des etudes de simulation montrent que la methode offre de bonnes performances avec des echantillons de taille finie. La methode est illustree au moyen d'une etude de cas dont les donnees portent sur les sarcomes des tissus mous de stade III. La revue canadienne de statistique 43: 1-15; 2014 (c) 2014 Societe statistique du Canada
引用
收藏
页码:635 / 649
页数:15
相关论文
共 50 条
  • [1] Semiparametric model and inference for spontaneous abortion data with a cured proportion and biased sampling
    Piao, Jin
    Ning, Jing
    Chambers, Christina D.
    Xu, Ronghui
    BIOSTATISTICS, 2018, 19 (01) : 54 - 70
  • [2] A class of semiparametric transformation models for survival data with a cured proportion
    Choi, Sangbum
    Huang, Xuelin
    Chen, Yi-Hau
    LIFETIME DATA ANALYSIS, 2014, 20 (03) : 369 - 386
  • [3] A class of semiparametric transformation models for survival data with a cured proportion
    Sangbum Choi
    Xuelin Huang
    Yi-Hau Chen
    Lifetime Data Analysis, 2014, 20 : 369 - 386
  • [4] Double Inverse-Gaussian Distributions and Associated Inference
    Almutairi, A.
    Ghitany, M. E.
    Alothman, A.
    Gupta, Ramesh C.
    JOURNAL OF THE INDIAN SOCIETY FOR PROBABILITY AND STATISTICS, 2023, 24 (02) : 151 - 182
  • [5] Double Inverse-Gaussian Distributions and Associated Inference
    A. Almutairi
    M. E. Ghitany
    A. Alothman
    Ramesh C. Gupta
    Journal of the Indian Society for Probability and Statistics, 2023, 24 : 151 - 182
  • [6] Semiparametric varying-coefficient model for interval censored data with a cured proportion
    Shao, Fang
    Li, Jialiang
    Ma, Shuangge
    Lee, Mei-Ling Ting
    STATISTICS IN MEDICINE, 2014, 33 (10) : 1700 - 1712
  • [7] A MIXED POISSON INVERSE-GAUSSIAN REGRESSION-MODEL
    DEAN, C
    LAWLESS, JF
    WILLMOT, GE
    CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE, 1989, 17 (02): : 171 - 181
  • [8] SEMIPARAMETRIC INFERENCE IN A MODEL FOR ASSOCIATION IN BIVARIATE SURVIVAL-DATA
    OAKES, D
    BIOMETRIKA, 1986, 73 (02) : 353 - 361
  • [9] PROPERTIES OF A MULTIVARIATE SURVIVAL DISTRIBUTION GENERATED BY A WEIBULL AND INVERSE-GAUSSIAN MIXTURE
    JAISINGH, LR
    DEY, DK
    GRIFFITH, WS
    IEEE TRANSACTIONS ON RELIABILITY, 1993, 42 (04) : 618 - 622
  • [10] Generalized inverse-Gaussian frailty models with application to TARGET neuroblastoma data
    Luiza S. C. Piancastelli
    Wagner Barreto-Souza
    Vinícius D. Mayrink
    Annals of the Institute of Statistical Mathematics, 2021, 73 : 979 - 1010