-
作者：HIROTSU, C
摘要：Row-wise and/or column-wise multiple comparison procedures are developed for elucidating the association involved in various types of 2-way contingency tables. They include multinomials with ordered categories and paired comparison data arranged in a 2-way table.
-
作者：BEDRICK, EJ
摘要：Holt. Scott and Ewings (1980) propose a modified Pearson .CHI.2 statistic for testing independence in a 2-way table of survey data. The multiplier of .CHI.2 needed for this modification is a weighted sum of cell and marginal cell design effects. A similar adjustment of the .CHI.2 and G2 statistics is possible whenever log linear models with closed form estimates are fitted to a cross-classified table of survey data.
-
作者：TONG, H
-
作者：MCLEISH, D; TOSH, D
作者单位：Acadia University
摘要：Suppose a low dose of a drug is administered and, if no response is observed, increase this dose by a fixed amount which is administered to a 2nd experimental subject. This procedure continues until, at some dose level, a response is finally observed. This whole sequence may be repeated. The features of an experimental design of this kind for estimating the dose at which the expected response is small were investigated. This design is highly efficient when the the number of responses, e.g., de...
-
作者：SAW, JG
摘要：A unit vector with m elements may be thought of as representing a direction in a space of m dimensions. Pairs of dependent unit vectors having prescribed marginal distributions are presented. Given 2 sets of unit vectors, an analysis for correlation between the 2 sets is proposed. The analysis presented is distribution free under a broad class of null distributions and thereby improves on an analysis recently suggested by Stephens (1979).
-
作者：LAN, KKG; DEMETS, DL
作者单位：University of Wisconsin System; University of Wisconsin Madison
摘要：Pocock (1977), O''Brien and Fleming (1979) and Slud and Wei (1982) have proposed different methods to construct discrete sequential boundaries for clinical trials. These methods require that the total number of decision times be specified in advance. A more flexible way to construct discrete sequential boundaries is proposed. The method is based on the choice of a function, .alpha.*(t), which characterizes the rate at which the error level .alpha. is spent. The boundary at a decision time is d...
-
作者：ROBERTSON, T; WRIGHT, FT
作者单位：University of Missouri System; Missouri University of Science & Technology
摘要：The use of much of the distribution theory developed for order restricted inference has been limited by the lack of algorithms for the level probabilities. An approximation for these, which accounts for the pattern of large and small weights, is developed. This approximation and the equal weights approximation are examined. Both approximations appear to be reasonable for weight sets having a moderate amount of variability. The quality of the equal weights approximation, as a function of the am...
-
作者：CHAUDHURI, A; ADHIKARY, AK
摘要：The efficiency of Midzuno and Sen''s strategy relative to a few estimators based on simple random sampling without replacement is studied under a postulated linear regression model with uncorrelated error and a .gamma.-distributed auxiliary character.
-
作者：SLUD, EV; RUBINSTEIN, LV
作者单位：National Institutes of Health (NIH) - USA; NIH National Cancer Institute (NCI)
摘要：In many contexts where there is interest in inferring the marginal distribution of a survival time T subject to censoring embodied in a latent waiting time C, the times T and C may not be independent. A new class of nonparametric assumptions on the conditional distribution of T given C and how they lead to consistent generalizations of the Kaplan and Meier (1958) survival curve estimator are presented. The new survival curve estimators are used under weak assumptions to construct bounds on the...
