RESUMO
We studied the problem of testing a hypothesized distribution in survival regression models when the data is right censored and survival times are influenced by covariates. A modified chi-squared type test, known as Nikulin-Rao-Robson statistic, is applied for the comparison of accelerated failure time models. This statistic is used to test the goodness-of-fit for hypertabastic survival model and four other unimodal hazard rate functions. The results of simulation study showed that the hypertabastic distribution can be used as an alternative to log-logistic and log-normal distribution. In statistical modeling, because of its flexible shape of hazard functions, this distribution can also be used as a competitor of Birnbaum-Saunders and inverse Gaussian distributions. The results for the real data application are shown. Copyright © 2017 John Wiley & Sons, Ltd.
Assuntos
Modelos Estatísticos , Modelos de Riscos Proporcionais , Análise de Sobrevida , Distribuição de Qui-Quadrado , Humanos , Modelos Logísticos , Distribuição NormalRESUMO
A survey of statistical methods for validation of shape-scale families of probability distributions from type II censored samples is given. We propose "integrated likelihood ratio tests" which are modifications of Zhang's tests from complete to type II censored data. We also give modifications of Cramér-von-Mises and Anderson-Darling tests using integration with respect to non-parametric estimators of the cumulative distribution function. Explicit formulas for modified chi-squared tests from censored data with data driven choice of partitioning are given. Powers of tests against most used alternatives to the Weibull, loglogistic and lognormal distribution are compared.
Assuntos
Bioestatística/métodos , Animais , Distribuição de Qui-Quadrado , Raios gama/efeitos adversos , Humanos , Funções Verossimilhança , Modelos Logísticos , Masculino , Camundongos , Lesões Experimentais por Radiação/mortalidade , Estatísticas não ParamétricasRESUMO
We propose new two and k-sample tests for evaluating the equality of survival distributions against alternatives that include crossing of survival functions, and proportional and monotone hazard ratios. The tests allow for right censored data. The asymptotic power against local alternatives is investigated. Simulation results demonstrate that the new tests are more powerful than known tests when survival functions cross. We apply the tests to a well known study of chemo- and radio-therapy conducted by the Gastrointestinal Tumor Study Group. The P-values for both proposed tests are much smaller than for other known tests.