借名制：民间信仰在当代的生存策略——烟台营子村关帝庙诞生的民族志

本文基于三年的参与观察和二十余例的个体访谈,采用了民族志方法叙述了一个蒙古族聚居村落采用名为“成吉思汗纪念馆”实际建造关帝庙的过程。认为：“借名制”是民间信仰在当代的一种生存策略,这个过程中包含了村民的努力、乡土权威的支持和政府部门的通融,是小传统在大小传统相互碰撞的空间里的文化反映,是缓解紧张关系、构建有机社会的一种生存艺术。     

闽台农产品贸易互补性实证研究

运用显性比较优势指数、相对显性优势指数和出口相似度指数分别从比较优势、相对比较优势、结构竞争角度对闽台农产品贸易互补性进行剖析。结果表明:相对世界平均水平,福建农产品出口具有较强比较优势,而台湾地区农产品出口不具有比较优势,福建相对台湾具有比较优势;闽台农产品存在结构性贸易互补,但互补性呈下降趋势。     

Fulton＇s猜想的另一种证法

讨论了带有耦合边界条件的自Sturm-Liouville问题．作为已有解决下标问题简单方法的应用,证明了Fulton’s猜想是正确的．     

Hierarchical-Likelihood Approach for Mixed Linear Models with Censored Data

Mixed linear models describe the dependence via random effects in multivariate normal survival data. Recently they have received considerable attention in the biomedical literature. They model the conditional survival times, whereas the alternative frailty model uses the conditional hazard rate. We develop an inferential method for the mixed linear model via Lee and Nelder's (1996) hierarchical-likelihood (h-likelihood). Simulation and a practical example are presented to illustrate the new method.     

Predicting Pareto and exponential observables

The author considers, from a Bayesian viewpoint, the problem of predicting a future fraction of observables that lie in a set when the present and future observables are Pareto-distributed. Exact solutions as well as convenient approximations are obtained for the censored case.     

Dose-response models for time-to-response toxicity data

This paper concerns the modelling and analysis of toxicity data in which the time to some toxic response is recorded and of importance. The paper begins with a review of a variety of dose-response models, including log-linear, proportional hazards, multievent, and compartmental models, that have been suggested and used in this context. Models for competing risks are also reviewed and several possible approaches are considered and discussed in the context of dose response experiments. The formulation of a model for competing risks that utilizes cause-specific hazards gives a natural basis for the modelling and analysis of certain experimental situations in which only partial information is available on the time to response. Such situations arise, for example, when the presence of tumour is not clinically detectable in carcinogenicity trials. Likelihood construction is discussed, and appropriate likelihood contributions are derived. The paper concludes with a discussion of measures of risk which take account of the time dependence of the toxic response under study.     

Bayesian Model Selection and Averaging in Additive and Proportional Hazards Models

Although Cox proportional hazards regression is the default analysis for time to event data, there is typically uncertainty about whether the effects of a predictor are more appropriately characterized by a multiplicative or additive model. To accommodate this uncertainty, we place a model selection prior on the coefficients in an additive-multiplicative hazards model. This prior assigns positive probability, not only to the model that has both additive and multiplicative effects for each predictor, but also to sub-models corresponding to no association, to only additive effects, and to only proportional effects. The additive component of the model is constrained to ensure non-negative hazards, a condition often violated by current methods. After augmenting the data with Poisson latent variables, the prior is conditionally conjugate, and posterior computation can proceed via an efficient Gibbs sampling algorithm. Simulation study results are presented, and the methodology is illustrated using data from the Framingham heart study.     

Explained Variation and Predictive Accuracy in General Parametric Statistical Models: The Role of Model Misspecification

When studying a regression model measures of explained variation are used to assess the degree to which the covariates determine the outcome of interest. Measures of predictive accuracy are used to assess the accuracy of the predictions based on the covariates and the regression model. We give a detailed and general introduction to the two measures and the estimation procedures. The framework we set up allows for a study of the effect of misspecification on the quantities estimated. We also introduce a generalization to survival analysis.     

Survival Models Based on the Ornstein-Uhlenbeck Process

When modelling survival data it may be of interest to imagine an underlying process leading up to the event in question. The Ornstein-Uhlenbeck process is a natural model to consider in a biological context because it stabilizes around some equilibrium point. This corresponds to the homeostasis often observed in biology, and also to some extent in the social sciences. First, we study the first-passage time distribution of an Ornstein-Uhlenbeck process, focussing especially on what is termed quasi-stationarity and the various shapes of the hazard rate. Next, we consider a model where the individual hazard rate is a squared function of an Ornstein-Uhlenbeck process. We extend known results on this model. The results on quasi-stationarity are relevant for recent discussions about mortality plateaus. In addition, we point out a connection to models for short-term interest rates in financial modeling.