-
作者：Robins, JM; Wang, NS
作者单位：Harvard University; Harvard T.H. Chan School of Public Health; Texas A&M University System; Texas A&M University College Station
摘要：We derive an estimator of the asymptotic variance of both single and multiple imputation estimators. We assume a parametric imputation model but allow for non- and semiparametric analysis models. Our variance estimator, in contrast to the estimator proposed by Rubin (1987), is consistent even when the imputation and analysis models are misspecified and incompatible with one another.
-
作者：Cribari-Neto, F; Ferrari, SLP; Cordeiro, GM
作者单位：Universidade Federal de Pernambuco; Universidade de Sao Paulo; Universidade Federal da Bahia
摘要：The heteroscedasticity-consistent covariance matrix estimator proposed by White (1980) is commonly used in practical applications and is implemented into a number of pieces of statistical software. However, although consistent, it can display substantial bias in small to moderately large samples, as shown by Monte Carlo simulations elsewhere. This paper defines modified White estimators which are approximately bias-free. Numerical results show that the modified estimators display much smaller ...
-
作者：Kent, JT; Dryden, IL; Anderson, CR
作者单位：University of Leeds; University of Nottingham
摘要：Grenander & Miller (1994) describe a model for representing amorphous two-dimensional objects with no obvious landmark. Each object is represented by n vertices around its perimeter, and is described by deforming an n-sided regular polygon using edge transformations. A multivariate normal distribution with a block circulant covariance matrix is used to model these edge transformations. The purpose of this paper is to describe in detail the statistical properties of this multivariate model and ...
-
作者：Yeo, IK; Johnson, RA
作者单位：Kangwon National University; University of Wisconsin System; University of Wisconsin Madison
摘要：We introduce a new power transformation family which is well defined on the whole real line and which is appropriate for reducing skewness and to approximate normality. It has properties similar to those of the Box-Cox transformation for positive variables, The large-sample properties of the transformation are investigated in the contect of a single random sample.
-
作者：Choi, E; Hall, P
作者单位：Australian National University
摘要：Motivated by spatial data on earthquake epicentres, we consider the problem of estimating properties of poles in point-process intensity functions. Our methods are semiparametric, requiring only 'asymptotic' models for the intensity. They produce estimates of the locations and strengths of poles. Strength is expressed in terms of an exponent of regular variation, and is simply related to the correlation dimension of the underlying point process. It is argued that existing methods for estimatin...
-
作者：Seber, GAF; Nyangoma, SO
作者单位：University of Auckland
摘要：Ordinary residuals from linear models are useful for diagnostic purposes. Unfortunately residuals from nonlinear models do not share the same useful properties, and Cook & Tsai (1985) introduced so-called projected residuals which overcome some of the problems. After setting up some second-order asymptotics, we briefly discuss various residuals used currently for multinomial models and introduce some new diagnostics including projected residuals. Two examples, from genetics and psychology, are...
-
作者：Li, G; Tiwari, RC; Wells, MT
作者单位：University of California System; University of California Los Angeles; University of North Carolina; University of North Carolina Charlotte; Cornell University
摘要：In studies to compare two samples, more information may be available on one treatment than the other. When one population is modelled parametrically and the other nonparametrically, we study large sample properties of a semiparametric sample quantile comparison function and show that it can have substantially smaller asymptotic variance than its nonparametric counterpart, especially near the boundaries. We describe applications to both two-sample tests and receiver operating characteristic cur...
-
作者：Newton, MA; Zhang, YL
作者单位：University of Wisconsin System; University of Wisconsin Madison
摘要：The mixture of Dirichlet processes posterior that arises in nonparametric Bayesian analysis has been analysed most effectively using Markov chain Monte Carlo. As a computationally simple alternative, we introduce a recursive approximation based on one-step posterior predictive distributions. Asymptotic calculations provide theoretical support for this approximation, and we investigate its actual behaviour in several numerical examples. From a non-Bayesian perspective, this new recursion may be...
-
作者：Hjellvik, V; Tjostheim, D
作者单位：Institute of Marine Research - Norway; University of Bergen
摘要：We propose a method of modelling panel time series: data with both inter- and intraindividual correlation, and of fitting an autoregressive model to such data. Estimators are obtained by a conditional likelihood argument. If there are few observations in each series, the estimators can be dramatically improved by Burg-type:estimators taking edge effects into account. The consequences of ignoring the intercorrelation term are analysed. Partial lack of consistency is demonstrated in this situati...
-
作者：Cavanaugh, JE; Johnson, WO
作者单位：University of Missouri System; University of Missouri Columbia; University of California System; University of California Davis
摘要：An important inferential objective in state space modelling is to recover unobserved states using fixed-interval smoothing. Thus, the identification of cases which have a substantial influence on the smoothers is a relevant practical problem. To facilitate this identification, we propose a case-deletion diagnostic which can be easily computed using the outputs of the standard filtering and smoothing algorithms. Our diagnostic is defined as the Kullback-Leibler directed divergence between two v...
