-
作者：WILLIAMS, JS; LAGAKOS, SW
作者单位：Colorado State University System; Colorado State University Fort Collins; State University of New York (SUNY) System; University at Buffalo, SUNY
摘要：In the analysis of survival-type variables arising from medical investigations, one is often faced with incomplete or right-censored observations. In many cases the mechanisms leading to censoring are intrinsically related to the survival variable and standard methods of analysis are not appropriate. Consequences are examined of the dependence of survival on the causes of censoring. Also examined are the testability of a set of data for the importance in survival inferences of the underlying c...
-
作者：SEAL, HL
作者单位：Swiss Federal Institutes of Technology Domain; Ecole Polytechnique Federale de Lausanne
摘要：Given 2 states A and B such that individuals in state A have mutually exclusive probabilities, possibly dependent on the time spent in state A, of leaving that state because of death, or passage to state B. The probability of an individual passing to state B and dying there within a given period was studied. This problem has been of great interest and importance to actuaries for over 100 yr and the solutions of their professional contemporaries have appeared in their textbooks. Twenty-five yea...
-
作者：TITTERINGTON, DM
作者单位：University of Glasgow
摘要：The procedure, due to Aitchison and Aitken (1976), of analyzing multivariate binary data by kernel methods was extended to deal with missing data problems. The performance of the techniques was discussed for univariate, bivariate and for specific multivariate data. Comparisons were drawn with other approaches.
-
作者：MCCULLAGH, P
作者单位：University of London; Imperial College London
摘要：Clayton (1974) proposed some simple odds-ratio statistics for comparing 2 independent samples of ordered categorical data. These ideas were extended to a related model for paired data. Two types of estimators were proposed and their efficiency and consistency were investigated. In the special case where there were only 2 categories the model reduces to Cox''s (1958) model for binary paired comparisons.
-
作者：WAHRENBERGER, DL; ANTLE, CE; KLIMKO, LA
作者单位：Pennsylvania Commonwealth System of Higher Education (PCSHE); Pennsylvania State University; Pennsylvania State University - University Park
摘要：Fox suggested and evaluated several non-Bayesian rules for the problem of the 2-armed bandit. Several Bayesian rules for this problem are compared with the best of Fox''s rules. If a reasonably appropriate prior is used, Bayesian rules are better than Fox''s rule. Bayesian rules are quite robust with regard to the choice of a prior. [This method has application to corresponding medical experiments.].
-
作者：GOUGH, KJ
作者单位：Newcastle University - UK
摘要：For many diseases an individual once infected is unable to pass on the disease for what is called the latent period. He then passes into the infectious period, which ends when his symptoms appear and he is removed from circulation. Several attempts to model this situation are described, with emphasis on a model in which the latent period and the infectious period are proportional to .chi.2 variates. The likelihood function is derived for data consisting of interremoval times from households of...
-
作者：BROWN, PJ
作者单位：Imperial College London; University of London
摘要：In biology, a sequence of binary or polytomous tests is used to identify the population of origin of a specimen. The sequence is controlled by a diagnostic key which specifies the next test to be applied conditional on the responses to the tests so far performed. Provided that at least some tests are free from error for some of the populations, the tests performed serve to eliminate certain populations from contention. This leads to constructing the key by choosing the most useful next test. H...
-
作者：CHAN, NN
作者单位：Chinese University of Hong Kong
-
作者：FAREWELL, VT
作者单位：Imperial College London; University of London
摘要：A binary variable can specify the incidence of a particular disease, Y = 1 or a lifetime free of the disease, Y = 0. In a study, some subjects have Y = 1 recorded at specified ages. For other subjects, with Y unknown due to incomplete follow-up, the observed follow-up time compared with the usual incidence pattern for the disease gives some information on the possibility that Y = 0. A model for this situation is proposed which combines a logistic relationship for the probability of incidence a...
-
作者：STEPHENS, MA
作者单位：McMaster University
摘要：A goodness of fit tests for the extreme value distribution was presented based on the empirical distribution function statistics W2, U2 and A2. Asymptotic percentage points were given for each of the 3 statistics and for the 3 cases where one or both of the parameters of the distribution must be estimated from the data. Slight modifications of the calculated statistics were given to enable the points to be used with small samples.
