-
作者：ROBERTSON, T; WRIGHT, FT
作者单位：University of Missouri System; Missouri University of Science & Technology
摘要：Chase (1974) found a moderately good approximation for the chi-bar-squared, .hivin..chi.2, and E-bar-squared, .hivin.E2, distributions for an important special case of comparing ordered dose levels with a zero control where there are more observations on the control. Chase''s results are sharpened and extended to include the case in which the increased precision is on an intermediate sample. This provides new information concerning the behavior of the .hivin..chi.2 and .hivin.E2 distributions ...
-
作者：MILLER, R; HALPERN, J
摘要：There are 4 regression techniques currently available for use with censored data which do not assume particular parametric families of survival distributions. They are due to Cox (1972), Miller (1976), Buckley and James (1979) and Koul, Susarla and Van Ryzin (1981). These 4 methods are described, and their performances compared on the updated Stanford heart transplant data. Conclusions on the usefulness of the 4 procedures are drawn.
-
作者：HALL, P
-
作者：SLUD, EV
摘要：Under various parameterizations of the 2-sample survival problem with nuisance hazards and fixed or independent right-censoring, the consistency and efficiency of maximum partial likelihood estimators and partial likelihood score tests are investigated rigorously. Consistency of estimation is typical but full efficiency of tests seems to hold generally only when regression parameters and nuisance parameters enter the hazard function symmetrically.
-
作者：STEWART, WH; PIERCE, DA
作者单位：Oregon State University
摘要：The efficiency of nonparametric survival analysis (Cox, 1972, 1975) relative to parametric analysis is examined for grouped data. This setting avoids the difficulties of partial likelihood and allows standard likelihood methods to apply. The results are similar to results for ungrouped data, but are perhaps more easily understood. Some insight is also gained for problems involving time-dependent covariables and for problems with many covariables.
-
作者：SIRVANCI, M; LEVENT, I
作者单位：George Washington University
-
作者：FAREWELL, VT
摘要：The effect of observation variability in the classification of an ordinal response is examined within the framework of the proportional hazards regression model for ordinal data. A model is proposed and incorporates this type of variability and the behavior of the proportional hazards model when this new model is appropriate is examined. Four data sets are used to illustrate the practical application of the model [i.e., nausea for 219 patients receiving chemotherapy with and without cisplatin;...
-
作者：CWIK, J; GOLEMBIEWSKA, M; KOWALCZYK, T; PLESZCZYNSKA, E
作者单位：University of Warsaw
摘要：Statistical concepts needed to formalize and solve problems of sister dependence are surveyed. Notions and measures of stochastic codependence are considered, and the joint use of the correlation coefficient and the monotone dependence function are discussed. Remarks on planning the analysis of experiments on sister cells are given. The results of experiments on Chilodonella steini serve as an illustration.
-
作者：HARRINGTON, DP; FLEMING, TR
作者单位：Mayo Clinic
摘要：A class of linear rank statistics is proposed for the k-sample problem with right-censored survival data. The class contains as special cases the log rank test (Mantel, 1966; Cox, 1972) and a test essentially equivalent to Peto and Peto''s (1972) generalization of the Wilcoxon test. Martingale theory is used to establish asymptotic normality of test statistics under the null hypotheses considered, and to derive expressions for asymptotic relative efficiencies under contiguous sequences of alte...
-
作者：DEMETS, DL; WARE, JH
作者单位：Harvard University; Harvard T.H. Chan School of Public Health
摘要：A group sequential method is proposed for the periodic analysis of accumulating data in clinical trials which are essentially 1-sided as in treatment-placebo studies. The proposed boundaries retain the early stopping properties of the procedure described previously by DeMets and Ware (1980) when treatment appears to be ineffective or harmful but incorporate the more stringent requirement of the model proposed by O''Brien and Fleming (1979) for early rejection of the null hypothesis in favor of...
