ACCELERATED FAILURE TIME MODELS WITH RANDOM EFFECTS TO ESTIMATE OPERATION TIME OF OIL WELLS

被引:0
作者
Santos, Patricia Borchardt [1 ]
Valenca, Dione Maria [1 ]
机构
[1] Univ Fed Rio Grande do Norte, CCET, BR-59072970 Natal, RN, Brazil
关键词
accelerated failure time models; correlated survival data; penalized likelihood; oil;
D O I
暂无
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
Correlated survival data arise in many contexts, as in recurrent failure times in repairable systems. Frailty models based on proportional hazards have been extensively considered to account for the dependence between failure times. We indicate how an alternative approach based on accelerated failure time (AFT) models with random effects may be implemented with an R function designed for fitting such models via penalized likelihood methods. We also carry out a simulation study to investigate the reliability of the proposed software and illustrate the procedure with data from a study conducted to estimate operation time of oil wells.
引用
收藏
页码:23 / 44
页数:22
相关论文
共 18 条
[1]  
Ascher H, 1984, REPAIRABLE SYSTEMS R
[2]   Testing homogeneity in Weibull-regression models [J].
Bolfarine, H ;
Valença, DM .
BIOMETRICAL JOURNAL, 2005, 47 (05) :707-720
[3]  
Collett D., 2003, MODELLING SURVIVAL D
[4]  
COX DR, 1972, J R STAT SOC B, V34, P187
[5]  
Dantas Maria Aldilene, 2010, Prod., V20, P127
[6]  
Demidenko E, 2004, MIXED MODELS THEORY, V518
[7]   NONPARAMETRIC-ESTIMATION FROM INCOMPLETE OBSERVATIONS [J].
KAPLAN, EL ;
MEIER, P .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1958, 53 (282) :457-481
[8]   A review of software packages for analyzing correlated survival data [J].
Kelly, PJ .
AMERICAN STATISTICIAN, 2004, 58 (04) :337-342
[9]   Parametric accelerated failure time models with random effects and an application to kidney transplant survival [J].
Lambert, P ;
Collett, D ;
Kimber, A ;
Johnson, R .
STATISTICS IN MEDICINE, 2004, 23 (20) :3177-3192
[10]  
Lawless JF., 2003, STAT MODELS METHODS, VSecond ed.