2004

最新文章

• Estimation in partially linear models with missing covariates AI翻译
  作者：Liang, H; Wang, SJ; Robins, JM; Carroll, RJ
  作者单位：Texas A&M University System; Texas A&M University College Station; Harvard University; Harvard T.H. Chan School of Public Health
  摘要：The partially linear model Y = X(T)beta + v(Z) + epsilon has been studied extensively when data are completely observed. In this article, we consider the case where the covariate X is sometimes missing, with missingness probability pi depending on (Y, Z). New methods are developed for estimating and v(.). Our methods are shown to outperform asymptotically methods based only on the complete data. Asymptotic efficiency is discussed. and the semiparametric efficient score function is derived. Jus...
• Multiple comparison of several linear regression models AI翻译
  作者：Liu, W; Jamshidian, M; Zhang, Y
  作者单位：University of Southampton; University of Southampton; California State University System; California State University Fullerton; State University System of Florida; University of Central Florida
  摘要：Research on multiple comparison during the past 50 years or so has focused mainly on the comparison of several population means. Several years ago. Spurrier considered the multiple comparison of several simple linear regression lines. He constructed simultaneous confidence bands for all of the contrasts of the simple linear regression lines over the entire range (-infinity, infinity) when the models have the same design matrices. This article extends Spurrier's work in several directions. Firs...
• The estimation of prediction error: Covariance penalties and cross-validation - Comment AI翻译
  作者：Burman, P
  作者单位：University of California System; University of California Davis
• The estimation of prediction error: Covariance penalties and cross-validation AI翻译
  作者：Efron, B
  作者单位：Stanford University
  摘要：Having constructed a data-based estimation rule, perhaps a logistic regression or a classification tree, the statistician would like to know its performance as a predictor of future cases. There are two main theories concerning prediction error: (I) penalty methods such as C-p, Akaike's information criterion, and Stein's unbiased risk estimate that depend on the covariance between data points and their corresponding predictions; and (2) cross-validation and related nonparametric bootstrap tech...
• Getting it right: Joint distribution tests of posterior simulators AI翻译
  作者：Geweke, J
  作者单位：University of Iowa; University of Iowa
  摘要：Analytical or coding errors in posterior simulators can produce reasonable but incorrect approxii nations of posterior moments. This article develops simple tests of posterior simulators that detect both kinds of errors, and uses them to detect and correct errors in two previously published articles. The tests exploit the fact that a Bayesian model specifies the joint distribution of observables (data) and unobservables (parameters). There are two joint distribution simulators. The roarginal-c...
• Testing for differences between conditional means in a time series context AI翻译
  作者：Ferreira, E; Stute, W
  作者单位：University of Basque Country; Justus Liebig University Giessen
  摘要：In this article we study tests for equality of two regression curves when the inputs are driven by a time series. The basic process underlying the test statistics is the empirical process of the time series marked by the difference in the pertaining dependent variables. The main results hold under strict stationarity of the input variables, but no mixing condition or special modeling of the time series will be necessary. A simulation study is reported on, which illustrates the quality of the d...
• Testing for trend in the presence of autoregressive error AI翻译
  作者：Roy, A; Falk, B; Fuller, WA
  作者单位：University System of Maryland; University of Maryland Baltimore County; Iowa State University
  摘要：A popular model for assessing dependence on time is the time series model composed of a linear trend plus a zero mean autoregressive (AR) process. Although considerable effort has been devoted developing tests for linear trend in the presence of serial correlation, the testing procedures used in practice are less than satisfactory for portions of the parameter space for the AR coefficient. This is because the variance of the feasible generalized least squares (FGLS) estimator of the trend coef...
• The estimation of prediction error: Covariance penalties and cross-validation - Comment AI翻译
  作者：Shen, XT; Huang, HC; Ye, JM
  作者单位：University of Minnesota System; University of Minnesota Twin Cities; Academia Sinica - Taiwan; City University of New York (CUNY) System; Baruch College (CUNY)
• Stable and efficient multiple smoothing parameter estimation for generalized additive models AI翻译
  作者：Wood, SN
  作者单位：University of Glasgow
  摘要：Representation of generalized additive models (GAM's) using penalized regression splines allows GAM's to be employed in a straightforward manner using penalized regression methods. Not only is inference facilitated by this approach, but it is also possible to integrate model selection in the form of smoothing parameter selection into model fitting in a computationally efficient manner using well founded criteria such as generalized cross-validation. The current fitting and smoothing parameter ...
• To model or not to model? competing modes of inference for finite population sampling AI翻译
  作者：Little, RJ
  作者单位：University of Michigan System; University of Michigan
  摘要：Finite population sampling is perhaps the only area of statistics in which the primary mode of analysis is based on the randomization distribution, rather than on statistical models for the measured variables. This article reviews the debate between design-based and model-based inference. The basic features of the two approaches are illustrated using the case of inference about the mean from stratified random samples. Strengths and weakness of design-based and model-based inference for surveys...