���ڳ�����α�������������ĺ�ѡ�����ݿ����������ƶ��о�

??How to solve the inference problem of candidate database web surveys is an urgent problem to be solved in the development of web survey. In order to solve this problem, the inference method of non-probability sampling based on superpopulation pseudo design and the combined sample is proposed. A superpopulation model is firstly built up to construct pseudo weights for a survey sample of the web candidate database. The estimator of the population mean is then computed according to the combined sample composed of the survey sample of the web candidate database and a probability sample. The variance estimator of the population mean estimator is lastly derived according to the variance estimation theory of the superpopulation model. The Bootstrap and Jackknife methods are also used to compute the variance estimator. And all these variance estimation methods are compared. The research results show that the population mean estimator based on superpopulation pseudo design and the combined sample is better, and has higher efficiency than the estimator only using the probability sample and the weighted estimator only using the survey sample of the web candidate database. The variance estimator computed by using the VM1, VM2 and VM3 method are relatively better.     

�̶�ЧӦ������ݲ�������ģ�͵ļ�Ȩ����LSDV����

This paper concerns with the estimation of a fixed effects panel data partially linear regression model with the idiosyncratic errors being an autoregressive process. For fixed effects short time series panel data, the commonly used autoregressive error structure fitting method will not result in a consistent estimator of the autoregressive coefficients. Here we propose an alternative estimation and show that the resulting estimator of the autoregressive coefficients is consistent and this method is workable for any order autoregressive error structure. Moreover, combining the B-spline approximation, profile least squares dummy variable (PLSDV) technique and consistently estimated the autoregressive error structure, we develop a weighted PLSDV estimator for the parametric component and a weighted B-spline series (BS) estimator for the nonparametric component. The weighted PLSDV estimator is shown to be asymptotically normal and more asymptotically efficient than the one which ignores the error autoregressive structure. In addition, this paper derives the asymptotic bias of the weighted BS estimator and establish its asymptotic normality as well. Simulation studies and an example of application are conducted to illustrate the finite sample performance of the proposed procedures.     

�ɲ����˶�����ά��������������һ�������ڵ����Զ������������������

??We study the linear quadratic optimal stochastic control problem which is jointly driven by Brownian motion and L\'{e}vy processes. We prove that the new affine stochastic differential adjoint equation exists an inverse process by applying the profound section theorem. Applying for the Bellman's principle of quasilinearization and a monotone iterative convergence method, we prove the existence and uniqueness of the solution of the backward Riccati differential equation. Finally, we prove that the optimal feedback control exists, and the value function is composed of the initial value of the solution of the related backward Riccati differential equation and the related adjoint equation.     

��˹ͼģ�͵Ļ����������Ľ���IPSP�㷨

The IPSP algorithm is an efficient algorithm for computing maximum likelihood estimation of Gaussian graphical models. It first divides clique marginals of graphical models into several groups, and then it adjusts clique marginals in each group locally. This paper uses the IIPS algorithm on junction tree to replace local adjustment on each group in the IPSP algorithm and propose a resulting algorithm called IPSP-JT to reduce the complexity of the IPSP algorithm. Moreover, we give a graph with minimum edges used by IIPS to adjust locally, and we prove its existence and uniqueness and construct a local junction tree. Numerical experiments show that the IPSP-JT algorithm runs faster than the IPSP algorithm for large Gaussian graphical models.     

����Ԫ���������������ķ��䵹�����΢�ַ�������Ԫ�ı�ʾ����

In this paper, we establish a local representation theorem for generators of reflected backward stochastic differential equations (RBSDEs), whose generators are continuous with linear growth. It generalizes some known representation theorems for generators of backward stochastic differential equations (BSDEs). As some applications, a general converse comparison theorem for RBSDEs is obtained and some properties of RBSDEs are discussed.     

�ع�ϵ���ļ�Ȩ��Ϲ�������С���˹��Ƶ����Ч��

本文研究随机约束下线性回归模型中, 回归系数的加权混合估计与最小二乘估计的相对效率, 并且给出了相对效率的上下界限. 最后我们给出了一个例子来验证我们的理论结果.     

�������ܶȱ�ģ���µ����ø�����Ϣ�ľ�����Ȼ��ֵ��

??Auxiliary population information is often available in finite population inference problems, and the empirical likelihood (EL) approach has been demonstrated to be flexible and useful for such problems. The present paper concerns EL when interest centers on inference for the mean of the baseline distribution under two-sample density ratio models. Although dual EL is a convenient technical tool since it has the same maximum point and maximum likelihood as DRM-based EL, it can not combine such auxiliary information into the likelihood conveniently and may have loss of efficiency. By contrast, the classical EL approach of Qin and Lawless\ucite{21} does not have this problem and incorporate seamlessly auxiliary information. Based on the EL using auxiliary information and the dual EL methods, we construct both point and interval estimations and make a careful comparison. Though the point estimation efficiency gain obtained by the former is not noticeable, we find that they may have different performances in interval estimation. In terms of coverage accuracy, the two intervals are comparable for not or moderate skewed populations, and the EL interval using auxiliary information can be much superior for severely skewed populations.     

һ�������Ȩ�͵Ľ����Լ���Ӧ��

This paper considers the asymptotics of randomly weighted sums and their maxima, where the increments {X_i,i\geq1\} is a sequence of independent, identically distributed and real-valued random variables and the weights {\theta_i,i\geq1\} form another sequence of non-negative and independent random variables, and the two sequences of random variables follow some dependence structures. When the common distribution F of the increments belongs to dominant variation class, we obtain some weakly asymptotic estimations for the tail probability of randomly weighted sums and their maxima. In particular, when the F belongs to consistent variation class, some asymptotic formulas is presented. Finally, these results are applied to the asymptotic estimation for the ruin probability.     

�������������϶����Ⱥ˵ĸ߽׵�������

Let p_M(t,x,y) be the minimal heat kernel of a d-dimenional compact Riemannian manifold M for any time t\in(0,1] and x,y\in M. Using the horizontal Brown bridge on M, we prove that, for any nonnegative integers n and m, there is a constant C depending on n,m and the manifold M, such that |\nabla^n_x\nabla^m_y\ln p_M(t,x,y)|\leq C[d(x,y)/t+1/\sqrt{t}\,]^{n+m}$, which generalizes the conclusion of the higher derivatives of the logarithmic heat kernel \ln p_M(t,x,y) about single variable in \ncite{1}.     

�����о��ĸ���

??This paper is based on ``Pao-Lu Hsu's lecture' (2019/3/22) at Peking University and the subsequent expansion of his reports. It begins with some recollections benefited of the author from Professor Hsu, and ends with thanking to a group of professors at Peking University for their support and help over the past decades. The middle part is the theme of the talk. It gives first an overview of personal cross research. Then, from a challenge of computing, the author reports on the study looking for a larger class of complex matrices which have real spectrum. This was done mainly in the last year. It involves the fields of computation, probability, statistical mechanics and quantum mechanics Next, the paper introduces the latest development of algorithms, which is another illustration of the intersection between probability theory and computational mathematics. As the end, it also outlines the understanding of the cross study.     

���ʷ��պͷ����׼��������Ͷ�ʺ��ٱ��ղ���

??It is assumed that both an insurance company and a reinsurance company adopt the variance premium principle to collect premiums. Specifically, an insurance company is allowed to investment not only in a domestic risk-free asset and a risky asset, but also in a foreign risky asset. Firstly, we use a geometry Brownian motion to model the exchange rate risk, and assume that the insurance company could control the insurance risk by transferring the insurance business into the reinsurance company. Secondly, the stochastic dynamic programming principle is used to study the optimal investment and reinsurance problems in two situations. The first is a diffusion approximation risk model and the second is a classical risk model. The optimal investment and reinsurance strategies are obtained under these two situations. We also show that the exchange rate risk has a great impact on the insurance company's investment strategies, but has no effect on the reinsurance strategies. Finally, a sensitivity analysis of some parameters is provided.     

Optimal Investment-Reinsurance Strategy with Exchange Rate Risk under Variance Premium Principl

It is assumed that both an insurance company and a reinsurance company adopt the variance premium principle to collect premiums. Specifically, an insurance company is allowed to investment not only in a domestic risk-free asset and a risky asset, but also in a foreign risky asset. Firstly, we use a geometry Brownian motion to model the exchange rate risk, and assume that the insurance company could control the insurance risk by transferring the insurance business into the reinsurance company. Secondly, the stochastic dynamic programming principle is used to study the optimal investment and reinsurance problems in two situations. The first is a diffusion approximation risk model and the second is a classical risk model. The optimal investment and reinsurance strategies are obtained under these two situations. We also show that the exchange rate risk has a great impact on the insurance company's investment strategies, but has no effect on the reinsurance strategies. Finally, a sensitivity analysis of some parameters is provided.     

最大熵——均值方差保费原则

本为利用熵在金融市场的两个功能;度量风险资产的投资风险和推测资产的概率分布,抓住了不确定性的本质,用熵值来度量由概率分布向信息转化的不确定性,建立了新的保费原则;最大熵—均值方差保费原则,使保费的制定更趋于合理.     

���ϱ���׼���������ٱ��չ�˾ΥԼ���յ������ٱ������

Based on the default risk effect of reinsurance company for reinsurer, this paper studies the optimal reinsurance strategy by VaR optimality criterion. In a reinsurance contract, reinsurance company will charge the number of premium to undertake part of the insurer's loss. However, if the reinsurance company's commitment exceeds its solvency, the default risk will occur. In order to avoid the default risk and minimize the total risk of the insurance company, the paper introduces Wang's premium principle to obtain the optimal reinsurance policy under VaR risk measure. Some numerical examples are given to illustrate these results.     

方差分量的二次不变估计的非负改进

研究一类方差分量模型中的方差分量的估计改进问题,首先在含两个方差分量模型中给出σ21二次型估计类,并且此估计类还具有无偏性和不变性.考虑二次损失(δ-θ)2,在此估计类基础上放弃无偏性进行非负改进,不仅得到优于二次不变无偏估计类的σ21的非负二次不变估计类,而且还说明了它优于方差分析估计和最小均方误差估计,文献[5]中给出s>2时的非负改进,但是非负改进存在是有条件的,本文克服了这个缺陷.最后给出了非负改进存在的充分必要条件.     

Statistical Inferences of Risk Premium under the Generalized Exponential Premium Theory

The principle of exponential premium is an important premium principle in non-life actuarial science. This paper proposes an improved exponential premium principle. This premium principle can not only include the principle of exponential premium as a special case, but also the generalizations of Esscher premium principle and net premium principle, which has many excellent properties as a premium principle. We study the maximal likelihood estimates, nonparametric estimates and Bayesian estimation of risk premium, and discuss the statistical properties including asymptotic unbiased, coincidence, and asymptotic normality. In addition, the asymptotic confidence interval for this risk premium is given. Finally, the convergence rate of maximum likelihood estimation and nonparametric estimation is compared by numerical simulation method. The results show that the nonparametric estimation has a small mean square error when the sample size is small.     

����ָ������ԭ���з��ձ��ѵ�ͳ���ƶ�

??The principle of exponential premium is an important premium principle in non-life actuarial science. This paper proposes an improved exponential premium principle. This premium principle can not only include the principle of exponential premium as a special case, but also the generalizations of Esscher premium principle and net premium principle, which has many excellent properties as a premium principle. We study the maximal likelihood estimates, nonparametric estimates and Bayesian estimation of risk premium, and discuss the statistical properties including asymptotic unbiased, coincidence, and asymptotic normality. In addition, the asymptotic confidence interval for this risk premium is given. Finally, the convergence rate of maximum likelihood estimation and nonparametric estimation is compared by numerical simulation method. The results show that the nonparametric estimation has a small mean square error when the sample size is small.     

指数保费原理下的经验厘定

在经典的信度理论中,信度保费是在净保费原理下得到的. 但是, 保险商业中, 保险公司要求制定的保费必须适用于某合适的保费原理以适应具体的保险商业的需要. 本文建立了指数保费原理下的完全经验厘定模型, 得到了风险保费的信度估计和经验Bayes 信度估计, 并讨论了结构参数的估计及其性质. 最后证明了多合同模型的经验Bayes 信度估计的渐近最优性     

正态-逆Wishart先验下多元线性模型中经验Bayes估计的优良性

在正态-逆Wishart先验下研究了多元线性模型中参数的经验Bayes估计及其优良性问题.当先验分布中含有未知参数时,构造了回归系数矩阵和误差方差矩阵的经验Bayes估计,并在Bayes均方误差(简称BMSE)准则和Bayes均方误差阵(简称BMSEM)准则下,证明了经验Bayes估计优于最小二乘估计.最后,进行了Monte Carlo模拟研究,进一步验证了理论结果.     

混合模型中方差分量估计的容许性及非负估计

对含有两个方差分量的线性混合模型, 本文构造了方差分量的一个线性估计类, 它包含许多常见的方差分量估计. 在这个类中我们建立了容许性的必要条件, 据此得到了两个新的改进估计. 最后我们讨论了方差分量的非负估计, 得到了优于方差分析估计和Tatsuya估计的正估计.