-
作者：Mathew, T; Sharma, MK; Nordström, K
作者单位：University System of Maryland; University of Maryland Baltimore; Johnson & Johnson; Johnson & Johnson USA; University of Helsinki
摘要：Let y(i) similar to N(Bx(i), Sigma), i = 1, 2,..., N, and y similar to N(B theta, Sigma) be independent multivariate observations, where the x(i)'s are known vectors, B, theta and Sigma are unknown, B being a positive definite matrix. The calibration problem deals with statistical inference concerning theta and the problem that we have addressed is the construction of confidence regions. In this article, we have constructed a region for theta based on a criterion similar to that satisfied by a...
-
作者：Neumann, MH
作者单位：Humboldt University of Berlin; Universite Catholique Louvain
摘要：We derive an approximation of a density estimator based on weakly dependent random vectors by a density estimator built from independent random vectors. We construct, on a sufficiently rich probability space, such a pairing of the random variables of both experiments that the set of observations (X-1,..., X-n) from the time series model is nearly the same as the set of observations (Y-1,..., Y-n) from the i.i.d. model. With a high probability, all sets of the form ((X-1,..., X-n)Delta(Y-1,...,...
-
作者：Läuter, J; Glimm, E; Kropf, S
作者单位：Otto von Guericke University
摘要：In this paper, a method for multivariate testing based on low-dimensional, data-dependent, linear scores is proposed. The new approach reduces the dimensionality of observations and increases the stability of the solutions. The method is reliable, even if there are many redundant variables. As a key feature, the score coefficients are chosen such that a left-spherical distribution of the scores is reached under the null hypothesis. Therefore, well-known tests become applicable in high-dimensio...
-
作者：Schapire, RE; Freund, Y; Bartlett, P; Lee, WS
作者单位：AT&T; Australian National University; Australian Defense Force Academy; University of New South Wales Sydney
摘要：One of the surprising recurring phenomena observed in experiments with boosting is that the test error of the generated classifier usually does not increase as its size becomes very large, and often is observed to decrease even after the training error reaches zero. In this paper, we show that this phenomenon is related to the distribution of margins of the training examples with respect to the generated voting classification rule, where the margin of an example is simply the difference betwee...
-
作者：Stute, W; Thies, S; Zhu, LX
作者单位：Justus Liebig University Giessen; Chinese Academy of Sciences
摘要：In the context of regression analysis it is known that the residual cusum process may serve as a basis for the construction of various omnibus, smooth and directional goodness-of-fit tests. Since a deeper analysis requires the decomposition of the cusums into their principal components and this is difficult to obtain, we propose to replace this process by its innovation martingale. It turns out that the resulting tests are (asymptotically) distribution free under composite null models and may ...
-
作者：Singh, K
作者单位：Rutgers University System; Rutgers University New Brunswick
摘要：A general formula for computing the breakdown point (in robustness) for the tth bootstrap quantile of a statistic T-n is obtained. The answer depends on t and the breakdown point of T-n. Since the bootstrap quantiles are vital ingredients of bootstrap confidence intervals, the theory has implications pertaining to robustness of bootstrap confidence intervals. For certain L and M estimators, a robustification of bootstrap is suggested via the notion of Winsorization.
-
作者：Barron, A; Hengartner, N
作者单位：Yale University
摘要：The asymptotic risk of efficient estimators with Kullback-Leibler loss in smoothly parametrized statistical models is k/2n, where k is the parameter dimension and n is the sample size. Under fairly general conditions, we given a simple information-theoretic proof that the set of parameter values where any arbitrary estimator is superefficient is negligible. The proof is based on a result of Rissanen that codes have asymptotic redundancy not smaller than (k/2)log n, except in a set of measure 0.
-
作者：Kushner, HB
作者单位：Nathan Kline Institute for Psychiatric Research
