-
作者：Stein, M. L.
作者单位：University of Chicago
摘要：Motivated by the study of annual temperature extremes, two new results on the limiting distribution of block maxima of random variables with varying upper bounds are obtained. One gives a generalized extreme value distribution as the limit, but with a different shape parameter from that obtained when the bound on the random variables does not vary. The other gives a limiting distribution that is only a generalized extreme value in certain cases. Both results consider triangular arrays of rando...
-
作者：Kim, J. K.; Yang, S.
作者单位：Iowa State University; North Carolina State University
摘要：Multiple imputation is popular for handling item nonresponse in survey sampling. Current multiple imputation techniques with complex survey data assume that the sampling design is ignorable. In this paper, we propose a new multiple imputation procedure for parametric inference without this assumption. Instead of using the sample-data likelihood, we use the sampling distribution of the pseudo maximum likelihood estimator to derive the posterior distribution of the parameters. The asymptotic pro...
-
作者：Ollier, E.; Viallon, V.
作者单位：Ecole Normale Superieure de Lyon (ENS de LYON); Universite Gustave-Eiffel; Universite Claude Bernard Lyon 1
摘要：We consider the estimation of regression models on strata defined using a categorical covariate, in order to identify interactions between this categorical covariate and the other predictors. A basic approach requires the choice of a reference stratum. We show that the performance of a penalized version of this approach depends on this arbitrary choice, and propose an approach that bypasses this at almost no additional computational cost. Regarding model selection consistency, our proposal mim...
-
作者：She, Yiyuan
作者单位：State University System of Florida; Florida State University
摘要：This paper studies simultaneous feature selection and extraction in supervised and unsupervised learning. We propose and investigate selective reduced rank regression for constructing optimal explanatory factors from a parsimonious subset of input features. The proposed estimators enjoy sharp oracle inequalities, and with a predictive information criterion for model selection, they adapt to unknown sparsity by controlling both rank and row support of the coefficient matrix. A class of algorith...
-
作者：Yu, Tao; Li, Pengfei; Qin, Jing
作者单位：National University of Singapore; University of Waterloo; National Institutes of Health (NIH) - USA; NIH National Institute of Allergy & Infectious Diseases (NIAID)
摘要：In this paper, we propose a method for estimating the probability density functions in a two-sample problem where the ratio of the densities is monotone. This problem has been widely identified in the literature, but effective solution methods, in which the estimates should be probability densities and the corresponding density ratio should inherit monotonicity, are unavailable. If these conditions are not satisfied, the applications of the resultant density estimates might be limited. We prop...
-
作者：Tsay, Ruey S.; Pourahmadi, Mohsen
作者单位：University of Chicago; Texas A&M University System; Texas A&M University College Station
摘要：Ensuring positive definiteness of an estimated structured correlation matrix is challenging. We show that reparameterizing Cholesky factors of correlation matrices using hyperspherical coordinates or angles provides a flexible and effective solution. Once a structured correlation matrix is identified, the corresponding angles and hence the constrained correlations may be estimated by maximum likelihood. Consistency and asymptotic normality of the maximum likelihood estimators of the angles are...
-
作者：Wang, Linbo; Robins, James M.; Richardson, Thomas S.
作者单位：Harvard University; Harvard T.H. Chan School of Public Health; Harvard University; Harvard T.H. Chan School of Public Health; University of Washington; University of Washington Seattle
摘要：Instrumental variables are widely used for estimating causal effects in the presence of unmeasured confounding. The discrete instrumental variable model has testable implications for the law of the observed data. However, current assessments of instrumental validity are typically based solely on subject-matter arguments rather than these testable implications, partly due to a lack of formal statistical tests with known properties. In this paper, we develop simple procedures for testing the bin...
-
作者：Wang, X.; Jiang, B.; Liu, J. S.
作者单位：Harvard University
摘要：Detecting dependence between two random variables is a fundamental problem. Although the Pearson correlation coefficient is effective for capturing linear dependence, it can be entirely powerless for detecting nonlinear and/or heteroscedastic patterns. We introduce a new measure, G-squared, to test whether two univariate random variables are independent and to measure the strength of their relationship. The G-squared statistic is almost identical to the square of the Pearson correlation coeffi...
-
作者：Sadinle, Mauricio; Reiter, Jerome P.
作者单位：Duke University
摘要：We introduce a nonresponse mechanism for multivariate missing data in which each study variable and its nonresponse indicator are conditionally independent given the remaining variables and their nonresponse indicators. This is a nonignorable missingness mechanism, in that nonresponse for any item can depend on values of other items that are themselves missing. We show that under this itemwise conditionally independent nonresponse assumption, one can define and identify nonparametric saturated...
-
作者：Fattorini, L.; Marcheselli, M.; Pisani, C.; Pratelli, L.
作者单位：University of Siena
摘要：We analyse design-based properties of two-phase strategies for estimating totals and nonlinear functions of totals for environmental populations when the sampling schemes are uniquely determined by points placed in the study region. In the first phase, points are located using tessellation stratified sampling, whereas in the second phase a finite population sampling scheme is adopted. We give sufficient conditions on second-phase designs that ensure consistency, and we investigate the variance...
