Penalized and Shrinkage Estimation in the Cox Proportional Hazards Model

This article considers the shrinkage estimation procedure in the Cox's proportional hazards regression model when it is suspected that some of the parameters may be restricted to a subspace. We have developed the statistical properties of the shrinkage estimators including asymptotic distributional biases and risks. The shrinkage estimators have much higher relative efficiency than the classical estimator, furthermore, we consider two penalty estimators—the LASSO and adaptive LASSO—and compare their relative performance with that of the shrinkage estimators numerically. A Monte Carlo simulation experiment is conducted for different combinations of irrelevant predictors and the performance of each estimator is evaluated in terms of simulated mean squared error. Simulation study shows that the shrinkage estimators are comparable to the penalty estimators when the number of irrelevant predictors in the model is relatively large. The shrinkage and penalty methods are applied to two real data sets to illustrate the usefulness of the procedures in practice.     

Inference under Heteroscedasticity of Unknown Form Using an Adaptive Estimator

The heteroscedasticity consistent covariance matrix estimators are commonly used for the testing of regression coefficients when error terms of regression model are heteroscedastic. These estimators are based on the residuals obtained from the method of ordinary least squares and this method yields inefficient estimators in the presence of heteroscedasticity. It is usual practice to use estimated weighted least squares method or some adaptive methods to find efficient estimates of the regression parameters when the form of heteroscedasticity is unknown. But HCCM estimators are seldom derived from such efficient estimators for testing purposes in the available literature. The current article addresses the same concern and presents the weighted versions of HCCM estimators. Our numerical work uncovers the performance of these estimators and their finite sample properties in terms of interval estimation and null rejection rate.     

Probabilistic Properties of Parametric Dual and Inverse Time Series Models Generated by ARMA Models

For the class of autoregressive-moving average (ARMA) processes, we examine the relationship between the dual and the inverse processes. It is demonstrated that the inverse process generated by a causal and invertible ARMA (p, q) process is a causal and invertible ARMA (q, p) model. Moreover, it is established that this representation is strong if and only if the generating process is Gaussian. More precisely, it is derived that the linear innovation process of the inverse process is an all-pass model. Some examples and applications to time reversibility are given to illustrate the obtained results.     

Stabilizing the Performance of Kurtosis Estimator of Multivariate Data

The estimation of the kurtosis parameter of the underlying distribution plays a central role in many statistical applications. The central theme of the article is to improve the estimation of the kurtosis parameter using a priori information. More specifically, we consider the problem of estimating kurtosis parameter of a multivariate population when some prior information regarding the the parameter is available. The rationale is that the sample estimator of the kurtosis parameter has a large estimation error. In this situation we consider shrinkage and pretest estimation methodologies and reappraise their statistical properties. The estimation based on these strategies yield relatively smaller estimation error in comparison with the sample estimator in the candidate subspace. A large sample theory of the suggested estimators are developed and compared. The results demonstrate that suggested estimators outperform the estimator based on the sample data only in the candidate subspace. In an effort to appreciate the relative behavior of the estimators in a finite sample scenario, a Monte-carlo simulation study is planned and performed. The result of simulation study strongly corroborates the asymptotic result. To illustrate the application of the estimators, some example are showcased based on recently published data.     

纪念苏丹商人穆罕默德·哈吉在华首设商务处

中国与阿拉伯非洲的历史交往源远流长,特别是与苏丹的联系,可以追溯到西汉时期,而且从那时起双方之间的往来一直延续不断.本文在历史回顾的基础上,通过实地调查和口传资料,着重考察了19世纪末苏丹商人穆罕默德·哈吉在广州首设商务办事处并开展苏(丹)中(国)贸易、加强双方社会联系的历史活动,揭示了苏中悠久关系史上鲜为人知的一页.     

New Methods for Evaluating Energy Infrastructure Development Risks

Many energy technologies that can provide reliable, low-carbon electricity generation are confined to nations that have access to robust technical and economic capabilities, either on their own or through geopolitical alliances. Equally important, these nations maintain a degree of institutional capacity that could lower the risks associated with deploying emergent energy technologies such as advanced nuclear or carbon capture and storage. The complexity, expense, and scrutiny that come with building these facilities make them infeasible choices for most nations. This paradigm is slowly changing, as the pressing need for low-carbon electricity generation and ongoing efforts to develop modular nuclear and carbon capture technologies have opened the door for potentially wider markets, including in nations without substantial institutional capacity. Here, using advanced nuclear technologies as our testbed, we develop new methods to evaluate national readiness for deploying complex energy infrastructure. Specifically, we use Data Envelopment Analysis—a method that eliminates the need for expert judgment—to benchmark performance across nations. We find that approximately 80% of new nuclear deployment occurs in nations that are in the top two quartiles of institutional and economic performance. However, 85% of potential low-carbon electricity demand growth is in nations that are in the bottom two quartiles of performance. We offer iconic paradigms for deploying nuclear power in each of these clusters of nations if the goal is to mitigate risk. Our research helps redouble efforts by industry, regulators, and international development agencies to focus on areas where readiness is low and risk correspondingly higher.     

Evaluating the Cost,Safety, and Proliferation Risks of Small Floating Nuclear Reactors

It is hard to see how our energy system can be decarbonized if the world abandons nuclear power, but equally hard to introduce the technology in nonnuclear energy states. This is especially true in countries with limited technical, institutional, and regulatory capabilities, where safety and proliferation concerns are acute. Given the need to achieve serious emissions mitigation by mid‐century, and the multidecadal effort required to develop robust nuclear governance institutions, we must look to other models that might facilitate nuclear plant deployment while mitigating the technology's risks. One such deployment paradigm is the build‐own‐operate‐return model. Because returning small land‐based reactors containing spent fuel is infeasible, we evaluate the cost, safety, and proliferation risks of a system in which small modular reactors are manufactured in a factory, and then deployed to a customer nation on a floating platform. This floating small modular reactor would be owned and operated by a single entity and returned unopened to the developed state for refueling. We developed a decision model that allows for a comparison of floating and land‐based alternatives considering key International Atomic Energy Agency plant‐siting criteria. Abandoning onsite refueling is beneficial, and floating reactors built in a central facility can potentially reduce the risk of cost overruns and the consequences of accidents. However, if the floating platform must be built to military‐grade specifications, then the cost would be much higher than a land‐based system. The analysis tool presented is flexible, and can assist planners in determining the scope of risks and uncertainty associated with different deployment options.     

Preservation properties for the mean residual life ordering

Sereral preservation results for the mean residual life (mr) ordering are given. In particular, we show that the mr-ordering is preserved under convolutions, mixtures and weak convergence.     

Efficient estimation for the conditional autoregressive model

Recently, spatial regression models have been attracting a great deal of attention in areas ranging from effect of traffic congestion on accident rates to the analysis of trends in gastric cancer mortality. In this paper, we propose efficient estimators for the regression coefficients of the spatial conditional autoregressive model, when uncertain auxiliary information is available about these coefficients. We provide efficiency comparisons of the proposed estimators based on asymptotic risk analysis and Monte Carlo simulations. We apply the proposed methods to real data on Boston housing prices and illustrate how a bootstrapping approach can be employed to compute prediction errors of the estimators.     

Confidence interval estimation for the population coefficient of variation using ranked set sampling: a simulation study

In this paper, an evaluation of the performance of several confidence interval estimators of the population coefficient of variation (τ) using ranked set sampling compared to simple random sampling is performed. Two performance measures are used to assess the confidence intervals for τ, namely: width and coverage probabilities. Simulated data were generated from normal, log-normal, skew normal, Gamma, and Weibull distributions with specified population parameters so that the same values of τ are obtained for each distribution, with sample sizes n=15, 20, 25, 50, 100. A real data example representing birth weight of 189 newborns is used for illustration and performance comparison.