A Log-Linear Regression Model for the Beta-Weibull Distribution

We introduce the log-beta Weibull regression model based on the beta Weibull distribution (Famoye et al., 2005; Lee et al., 2007). We derive expansions for the moment generating function which do not depend on complicated functions. The new regression model represents a parametric family of models that includes as sub-models several widely known regression models that can be applied to censored survival data. We employ a frequentist analysis, a jackknife estimator, and a parametric bootstrap for the parameters of the proposed model. We derive the appropriate matrices for assessing local influences on the parameter estimates under different perturbation schemes and present some ways to assess global influences. Further, for different parameter settings, sample sizes, and censoring percentages, several simulations are performed. In addition, the empirical distribution of some modified residuals are displayed and compared with the standard normal distribution. These studies suggest that the residual analysis usually performed in normal linear regression models can be extended to a modified deviance residual in the proposed regression model applied to censored data. We define martingale and deviance residuals to evaluate the model assumptions. The extended regression model is very useful for the analysis of real data and could give more realistic fits than other special regression models.

[1]  M. B. Rajarshi,et al.  Bathtub distributions: a review , 1988 .

[2]  Lee J. Bain,et al.  An exponential power life-testing distribution , 1975 .

[3]  J. Harley,et al.  A step-up procedure for selecting variables associated with survival. , 1975, Biometrics.

[4]  Vicente G Cancho,et al.  Generalized log-gamma regression models with cure fraction , 2009, Lifetime data analysis.

[5]  Debasis Kundu,et al.  Generalized Rayleigh distribution: different methods of estimations , 2005, Comput. Stat. Data Anal..

[6]  Gordon Johnston,et al.  Statistical Models and Methods for Lifetime Data , 2003, Technometrics.

[7]  Peter M. Bentler,et al.  Pseudo maximum likelihood estimation in elliptical theory: effects of misspecification , 1994 .

[8]  Feng-Chang Xie,et al.  Diagnostics analysis in censored generalized Poisson regression model , 2007 .

[9]  S. Ghosal.  Semiparametric Accelerated Failure Time Models for Censored Data , 2006 .

[10]  Heleno Bolfarine,et al.  Influence diagnostics in exponentiated-Weibull regression models with censored data , 2006 .

[11]  Luis A. Escobar,et al.  Assessing influence in regression analysis with censored data. , 1992, Biometrics.

[12]  David Hinkley,et al.  Bootstrap Methods: Another Look at the Jackknife , 2008 .

[13]  Anthony C. Davison,et al.  Bootstrap Methods and Their Application , 1998 .

[14]  B. Manly.  Randomization, Bootstrap and Monte Carlo Methods in Biology , 2018 .

[15]  Francisco Louzada-Neto,et al.  Influence diagnostics for polyhazard models in the presence of covariates , 2008, Stat. Methods Appl..

[16]  P. Grambsch,et al.  Martingale-based residuals for survival models , 1990 .

[17]  A. Hossain,et al.  A comparative study on detection of influential observations in linear regression , 1991 .

[18]  R. Cook.  Assessment of Local Influence , 1986 .

[19]  Heleno Bolfarine,et al.  Deviance residuals in generalised log-gamma regression models with censored observations , 2008 .

[20]  B. Efron,et al.  Bootstrap confidence intervals , 1996 .

[21]  P. McCullagh,et al.  Generalized Linear Models , 1992 .

[22]  Gilberto A. Paula,et al.  Log-modified Weibull regression models with censored data: Sensitivity and residual analysis , 2008, Comput. Stat. Data Anal..

[23]  Robert Tibshirani,et al.  An Introduction to the Bootstrap , 1994 .

[24]  J. Ibrahim,et al.  Perturbation selection and influence measures in local influence analysis , 2007, 0803.2986.

[25]  G. Cordeiro,et al.  Transformed generalized linear models , 2009 .

[26]  Mauricio Lima Barreto,et al.  Log-Burr XII regression models with censored data , 2008, Comput. Stat. Data Anal..

[27]  R. Cook.  Detection of influential observation in linear regression , 2000 .

[28]  Daniel Peña,et al.  The likelihood displacement: A unifying principle for influence measures , 1988 .

[29]  Heping Zhang,et al.  A diagnostic procedure based on local influence , 2004 .

[30]  Anthony C. Davison,et al.  Regression model diagnostics , 1992 .

[31]  Yu. A. Brychkov,et al.  Integrals and series , 1992 .

[32]  J. Klein,et al.  Survival Analysis: Techniques for Censored and Truncated Data , 1997 .

[33]  P. McCullagh,et al.  Generalized Linear Models, 2nd Edn. , 1990 .

[34]  D. Kundu,et al.  Theory & Methods: Generalized exponential distributions , 1999 .

[35]  Jeremy MG Taylor,et al.  Robust Statistical Modeling Using the t Distribution , 1989 .

[36]  Min Xie,et al.  Reliability analysis using an additive Weibull model with bathtub-shaped failure rate function , 1996 .

[37]  M. Puterman,et al.  Mixed Poisson regression models with covariate dependent rates. , 1996, Biometrics.

[38]  H. Bolfarine,et al.  A Bayesian analysis of the exponentiated-Weibull distribution , 1999 .

[39]  Gauss M. Cordeiro,et al.  Computational Statistics and Data Analysis a Generalized Modified Weibull Distribution for Lifetime Modeling , 2022 .

[40]  Felix Famoye,et al.  Journal of Modern Applied StatisticalMethods Beta-Weibull Distribution: Some Properties and Applications to Censored Data , 2022 .

[41]  Stuart R. Lipsitz,et al.  Using the jackknife to estimate the variance of regression estimators from repeated measures studies , 1990 .

[42]  D. N. Prabhakar Murthy,et al.  A modified Weibull distribution , 2003, IEEE Trans. Reliab..

[43]  Abdus S Wahed,et al.  A new generalization of Weibull distribution with application to a breast cancer data set. , 2009, Statistics in medicine.

[44]  Z. Ying,et al.  Rank-based inference for the accelerated failure time model , 2003 .

[45]  Gauss M. Cordeiro,et al.  The log-exponentiated Weibull regression model for interval-censored data , 2010, Comput. Stat. Data Anal..

[46]  E Lesaffre,et al.  Local influence in linear mixed models. , 1998, Biometrics.

[47]  U. Hjorth.  A Reliability Distribution With Increasing, Decreasing, Constant and Bathtub-Shaped Failure Rates , 1980 .

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

[49]  Kang-Mo Jung.  Local Influence in Generalized Estimating Equations , 2008 .

[50]  Deo Kumar Srivastava,et al.  The exponentiated Weibull family: a reanalysis of the bus-motor-failure data , 1995 .

[51]  E. Stacy.  A Generalization of the Gamma Distribution , 1962 .

[52]  Heleno Bolfarine,et al.  The Log-exponentiated-Weibull Regression Models with Cure Rate: Local Influence and Residual Analysis , 2021, Journal of Data Science.

[53]  Heleno Bolfarine,et al.  Influence diagnostics in generalized log-gamma regression models , 2003, Comput. Stat. Data Anal..