Scheduling parallel conference sessions: an application of a novel hybrid clustering algorithm for ensuring constrained cardinality

The 2011 World Statistics Congress included approximately 1150 oral and 250 poster presentations over approximately 250 sessions, with as many as 20 sessions running in parallel at any one time. Scheduling a timetable for such a conference is hence a complicated task, as ideally, talks on similar topics should be scheduled in the same session, and similar session topics should not be presented at identical times, allowing participants to easily decide which of the number of sessions to attend. Here, we consider a novel hybrid clustering algorithm that allows a solution under a constraint of fixed cardinality, and which is designed to find clusters of highly dense regions whilst forming others from the remaining outlying regions, hence providing a simple, yet data-generated, solution to such scheduling problems.     

Optimum treatment allocation for dual-objective clinical trials with binary outcomes

A common problem in randomized controlled clinical trials is the optimal assignment of patients to treatment protocols, The traditional optimal design assumes a single criterion, although in reality, there are usually more than one objective in a clinical trial. In this paper, optimal treatment allocation schemes are found for a dual-objective clinical trial with a binary response. A graphical method for finding the optimal strategy is proposed and illustrative examples are discussed.     

An application of linear feature selection to estimation of proportions

Let X be a random n-vector whose density function is given by a mixture of known multivariate normal density functions where the corresponding mixture proportions (a priori probabilities) are unknown. We present a numerically tractable method for obtaining estimates of the mixture proportions based on the linear feature selection technique of Guseman, Peters and Walker (1975).     

Improving the Numerical Performance of Static and Dynamic Aggregate Discrete Choice Random Coefficients Demand Estimation

The widely used estimator of Berry, Levinsohn, and Pakes (1995) produces estimates of consumer preferences from a discrete‐choice demand model with random coefficients, market‐level demand shocks, and endogenous prices. We derive numerical theory results characterizing the properties of the nested fixed point algorithm used to evaluate the objective function of BLP's estimator. We discuss problems with typical implementations, including cases that can lead to incorrect parameter estimates. As a solution, we recast estimation as a mathematical program with equilibrium constraints, which can be faster and which avoids the numerical issues associated with nested inner loops. The advantages are even more pronounced for forward‐looking demand models where the Bellman equation must also be solved repeatedly. Several Monte Carlo and real‐data experiments support our numerical concerns about the nested fixed point approach and the advantages of constrained optimization. For static BLP, the constrained optimization approach can be as much as ten to forty times faster for large‐dimensional problems with many markets.     

The multiplier method in constrained estimation of covariance structure models

Based on the multiplier method of constrained minimization, an algorithm is developed to handle the constrained estimation problem in covariance structure analysis. In the context of a general model which has wide applicability in multivariate medical and behavioural researches, computer programs are implemented to produce the weighted least squares estimates and the maximum likelihood estimates. The multiplier method is compared with the penalty function method in terms of computer time, number of iterations and number of unconstrained minimizations. The indication is that the multiplier method is substantially better.     

Is the Disposition of Constrained Maximization Chosen Rationally?

One of the most important issues in moral philosophy is whether morality can be justified by rationality. The purpose of this study is to examine Gauthier’s moral theory, focusing on the disposition of constrained maximization, which is the main thrust of his project to justify morality rationally. First of all, I shall investigate Gauthier’s assumption and condition for the rationality of the disposition of constrained maximization so as to disclose that the disposition of constrained maximization is not necessarily chosen by rational agents. Then I shall explore his other arguments including ones for the reinterpretation of rationality and the self-critical reflection of rational beings, which can be considered as his further efforts to make the disposition of constrained maximization a rational choice. By exploring them, I shall attempt to indicate that those arguments are not valid so long as he clings to the maximizing conception of rationality and thereby this conception of rationality itself is not enough to provide morality with a basis.     

An exchange heuristic for resource constrained scheduling with consideration given to opportunities for parallel processing

This paper describes a heuristic which produces efficient makespans for resource-constrained scheduling problems with parallel processing capabilities. This heuristic was initially developed for the scheduling of army battalion training exercises. The original heuristic has also been successfully applied to solve problems in project scheduling with limited resources, generalized job shop scheduling, and resource-constrained scheduling. The exchange heuristic requires an initial feasible solution upon which it improves the makespan by efficiently and systematically shuffling activities while maintaining feasibility. The method has recently been modified twice, termed the intelligent version and naive version, respectively, such that its ability to reduce the initial makespan is enhanced. In this study     

基于罚函数法的神经网络优化设计研究

介绍了Hopfidd神经网络系统的优化原理，从中提取反映网络动力学规律的非线性微分方程组，并用Matlab求解该方程组．算例表明，求解反映Hopfield网络运动的微分方程组能够解决优化问题．     

On the Relationship between Directional and Omnibus Statistical Tests

Abstract.  A common statistical problem involves the testing of a K -dimensional parameter vector. In both parametric and semiparametric settings, two types of directional tests – linear combination and constrained tests – are frequently used instead of omnibus tests in hopes of achieving greater power for specific alternatives. In this paper, we consider the relationship between these directional tests, as well as their relationship to omnibus tests. Every constrained directional test is shown to be asymptotically equivalent to a specific linear combination test under a sequence of contiguous alternatives and vice versa. Even when the direction of the alternative is known, the constrained test in general will not be optimal unless the objective function used to derive it is efficient. For an arbitrary alternative, insight into the power characteristics of directional tests in comparison to omnibus tests can be gained by a chi-square partition of the omnibus test.     

Maximum likelihood estimation of un1modal and decreasing densities based on arbitrarily right-censored data

Nonparametric maximum likelihood estimation of decreasing and unimodal density functions based on observations subject to arbitrary right censorship is considered. The maximum likelihood estimator of both types of densities is shown to exist and is a step function. The estimators may be computed for small samples by maximizing nonlinear equations subject to linear constraints, and the SUMT algorithm for constrained nonlinear optimization is used for the necessary calculations in an example.