Reliability analysis for stress-strength model from a general family of truncated distributions under censored data

Abstract

Under progressive Type-II censoring, inference of stress-strength reliability (SSR) is studied for a general family of lower truncated distributions. When the lifetime models of the strength and stress variables have arbitrary and common parameters, maximum likelihood and pivotal quantities based generalized estimators of SSR are established, respectively. Confidence intervals are constructed based on generalized pivotal quantities and bootstrap technique under different parameter cases as well. In addition, to compare the equivalence of the strength and stress parameters, likelihood ratio testing of interested parameters is provided as a complementary. Simulation studies and two real-life data examples are provided to investigate the performance of proposed methods.     

Stable International Environmental Agreements with a Stock Pollutant,Uncertainty and Learning

In this paper I address the question of how uncertainty about damage costs and the possibility of resolving that uncertainty in the future affects the incentives for countries to join an international environmental agreement. I use a two-period model with a stock pollutant where the number of countries generating pollution can be arbitrarily large. The stability concept employed is such that size of the stable IEA can be anywhere between 2 and the grand coalition of all countries depending on parameter values. The dynamic structure allows two different membership rules for an IEA: fixed (countries commit at the outset to be members for both periods) or variable (countries decide each period whether to join). I show that with fixed membership learning results in at least as high membership and global welfare as no learning (unless both the expected value and variance of damage costs are high). With variable membership, learning leads to higher membership (in the second period) but lower global welfare than no learning. For most parameter values variable membership results in higher global welfare than fixed membership.     

Back-to-back mixtures of discrete distributions

A method for expanding the choices for fits of discrete data is given. The method is very simple: a breakpoint is chosen for the data set on either side of which two separate discrete distributions are fit. Thus, the method is a mixture of two discrete distributions. The method is appealing in light of the ease with which the likelihood equations simplify. For illustrative purposes, the method is used on the data set that motivated its conception.     

以塑性应变和损伤为参变量的广义非局部损伤本构方程

将塑性应变和非局部损伤取为内变量，引入耗散势，利用连续介质损伤力学和热力学第二定律，建立了一个能全面描述材料本构行为的非局部非弹性损伤本构方程，用该模型计算了单位、单压状态下混凝土材料及20#钢的应力-应变关系曲线，取得了较好的结果．     

步进电机最佳变频控制研究

通过讨论功率步进电机的运行频率与输出转矩之间的动力学关系,提出了电机输出最大转矩的变频控制新方法。该方法对机床等机械设备进行技术改造,实现经济型数控系统具有实用价值。     

对德奥弗拉斯特在逻辑史上的贡献的再认识

德奥弗拉斯特跳出亚里士多德直言三段论又为人类逻辑贡献了假言、选言三段论,其创造性学说一直被错误地视为命题逻辑。德奥弗拉斯特本意在于开拓新逻辑关系,挖掘新研究对象,并非在意变项为何形式。后人臆测其变项为命题,从而归为命题逻辑,这是以分析方法混淆了研究对象。斯多葛命题逻辑并未发展德奥弗拉斯特学说,直到现代数理逻辑都是走了另一条路。正确认识德奥弗拉斯特的贡献,才能明辨普通逻辑的方向。     

当前宏观经济现时预测研究综述

宏观经济现时预测具有重要的现实意义。如何有效地利用大数据时代丰富的数据资源进行宏观经济现时预测已成为一个重要的研究课题。在梳理现有研究的基础上,对主流的宏观经济现时预测模型进行系统介绍,并就其预测能力进行分析比较,然后阐述当前现时预测可用的信息集及预测变量选取方法,再对中国宏观经济现时预测的现状做出评价,最后指出当前研究的不足与未来研究的主要方向,旨在为实证研究者提供技术参考。     

投入产出模型的动态化

建立合理、实用的动态投入产出模型,一直是投入产出理论研究的重要课题。本文把静态列昂节夫投入产出模型和宏观经济学的收入决定理论结合起来,得到一个基于变结构控制的动态投入产出模型。     

改进粒子群优化算法在电源规划中的应用

电源规划是一类复杂、非线性组合优化问题.传统的方法随着规划期的延长,考虑因素的增多,难以有效的进行优化,在实际应用中作用有限.首先,对电源规划优化问题进行了建模.然后,对于粒子群(PSO)的迭代策略进行改进,在此基础上,运用遗传粒子群(GPHA)混合优化算法进行了优化尝试.考虑到电源规划中相关参数众多,在优化过程中引入了虚拟变量对电源规划中的问题进行了简化描述;GHPA算法的适应度评价函数设计中,运用了罚函数的思想,以提高算法优化的效果.最后本文使用某省实际负荷预测和系统负荷实际数据,进行了电源规划方案优化,得到了优化后的电源规划方案,并与普通的遗传算法、粒子群算法以及传统的动态规划算法得到的结果进行了比较.比较的结果显示出了本文提出的算法在优化结果和速度方面具有明显效果.     

多标准决策表中发现概率规则的变精度粗糙集方法

用优势关系代替不可分辨关系,本文提出了一种可以从多标准决策表中获取概率规则的扩展变精度粗糙集模型,该模型能够处理多标准决策表中可能的不一相容性,获取由偏好对象组成的概率决策规则集,并导出事例决策系统的偏好模型。研究结果表明:基于优势关系,从多标准决策表中获取的最小概率规则集,使用的条件数量较少,且导出规则的数量较少、较强。