Exact filtering for partially observed continuous time models

Summary.  The forward–backward algorithm is an exact filtering algorithm which can efficiently calculate likelihoods, and which can be used to simulate from posterior distributions. Using a simple result which relates gamma random variables with different rates, we show how the forward–backward algorithm can be used to calculate the distribution of a sum of gamma random variables, and to simulate from their joint distribution given their sum. One application is to calculating the density of the time of a specific event in a Markov process, as this time is the sum of exponentially distributed interevent times. This enables us to apply the forward–backward algorithm to a range of new problems. We demonstrate our method on three problems: calculating likelihoods and simulating allele frequencies under a non-neutral population genetic model, analysing a stochastic epidemic model and simulating speciation times in phylogenetics.     

DES算法的安全误区

在对DES算法原理的描述和分析的基础上，论证DEC算法在应用中会导致安全性被破坏且容易被忽视的误区，并给出避开DES算法应用误区的具体操作方法．     

ERP环境下的模拟成本决策

ERP是在MRPII的基础上扩展了管理范围 ,其核心思想是供应链管理 ,在ERP系统支撑下 ,利用模拟成本数据对报价方案进行了分析比较 ,为企业快速、合理的报价提供了有效的解决方法。     

THE GROUPING PROBLEM IN DISTRIBUTION-FREE PLANAR REGRESSION

In the planar regression model having two slope parameters and identically distributed errors, exact distribution-free inference about one parameter may be carried out by grouping the observations, eliminating the nuisance parameter and reducing the model to simple linear regression, allowing exact distribution-free methods for slope to be employed. This model reduction involves a loss of efficiency: the choice of an optimal grouping to minimize efficiency loss is discussed.     

Sampling from multimodal distributions using tempered transitions

I present a new Markov chain sampling method appropriate for distributions with isolated modes. Like the recently developed method of simulated tempering, the tempered transition method uses a series of distributions that interpolate between the distribution of interest and a distribution for which sampling is easier. The new method has the advantage that it does not require approximate values for the normalizing constants of these distributions, which are needed for simulated tempering, and can be tedious to estimate. Simulated tempering performs a random walk along the series of distributions used. In contrast, the tempered transitions of the new method move systematically from the desired distribution, to the easily-sampled distribution, and back to the desired distribution. This systematic movement avoids the inefficiency of a random walk, an advantage that is unfortunately cancelled by an increase in the number of interpolating distributions required. Because of this, the sampling efficiency of the tempered transition method in simple problems is similar to that of simulated tempering. On more complex distributions, however, simulated tempering and tempered transitions may perform differently. Which is better depends on the ways in which the interpolating distributions are deceptive.     

A robust support vector machine for labeling errors

Support vector machine (SVM) is sparse in that its classifier is expressed as a linear combination of only a few support vectors (SVs). Whenever an outlier is included as an SV in the classifier, the outlier may have serious impact on the estimated decision function. In this article, we propose a robust loss function that is convex. Our learning algorithm is more robust to outliers than SVM. Also the convexity of our loss function permits an efficient solution path algorithm. Through simulated and real data analysis, we illustrate that our method can be useful in the presence of labeling errors.     

Approximating the projection depth median of dimensions p ⩾ 3

As a multivariate generalization of the univariate median, projection depth median (PM) is unique, and enjoys a very high breakdown point, much higher than its affine equivariant competitors such as halfspace depth median. Nevertheless, its computation is challenging. Until now PM can only be exactly computed efficiently for bivariate data. In this article, we develop an algorithm to approximate PM in higher dimensions. Some data examples indicate that the proposed algorithm performs well in terms of both accuracy and efficiency. As an application, we investigate the finite sample relative efficiency of PM by utilizing the Matlab implementation of this algorithm.     

Mean and cell-mean imputation resulting in the use of a semicontinuous distribution and a mixture of semicontinuous distributions

Zero-inflated models are commonly used for modeling count and continuous data with extra zeros. Inflations at one point or two points apart from zero for modeling continuous data have been discussed less than that of zero inflation. In this article, inflation at an arbitrary point α as a semicontinuous distribution is presented and the mean imputation for a continuous response is discussed as a cause of having semicontinuous data. Also, inflation at two points and generally at k arbitrary points and their relation to cell-mean imputation in the mixture of continuous distributions are studied. To analyze the imputed data, a mixture of semicontinuous distributions is used. The effects of covariates on the dependent variable in a mixture of k semicontinuous distributions with inflation at k points are also investigated. In order to find the parameter estimates, the method of expectation–maximization (EM) algorithm is used. In a real data of Iranian Households Income and Expenditure Survey (IHIES), it is shown how to obtain a proper estimate of the population variance when continuous missing at random responses are mean imputed.     

大样本线性回归模型的子抽样及变量选择

文章考虑了大样本下线性回归中同时进行快速估计和变量选择的问题,即针对一个存在稀疏解的大样本线性模型,根据重要性抽样分布从全数据集抽取少量子样本,对该子样本进行自适应Lasso估计。通过随机模拟研究,将该算法分别应用在几种不同的数据集中,并从模型预测精度和可解释性两个方面比较了四种子抽样方法在该算法下的表现。模拟结果表明,所提出的算法具有良好表现,在计算开销上也具有一定优势。     

Study on Multi-Trip Vehicle Routing Problem with Stochastic Simultaneous Pickup-Delivery Demand

Characterized by high service efficiency and low vehicle cost, multi-trip distribution allows the vehicle to travel multiple times between the distribution center and customers in order to complete the delivery task. Dynamic and uncertain customer demand is common during delivery. Combined pickup-delivery integration pattern with stochastic customer demand, an optimization model for multi-trip vehicle routing problem is set up with stochastic simultaneous pickup-delivery demand. Due to the sudden and simultaneous pickup-delivery of dynamic demand, the original distribution scheme needs to be optimized and adjusted, and the multi-trip routing adjustment strategy of "real-time flexible point" is proposed. According to the stochastic characteristics of the optimization model, a stochastic chance-constrained programming transformation model is introduced. A hybrid algorithm with nested stochastic simulation and variable neighborhood tabu search algorithm is designed to find the optimal distribution path. Finally, an example shows that the optimization model and algorithm are feasible and effective.