Large Deviation and Other Results for Minimum Contrast Estimators

A number of authors have been concerned with constructing large deviation approximations to densities and probabilities associated with minimum contrast estimators (equivalently, M-estimators) using a tilting approach due to Field. These developments are an interesting and important extension of saddlepoint-type methodology. However, in the case of a multivariate parameter, the theoretical picture has remained incomplete in certain respects, as explained below. In this paper we present results which provide rigorous justification of the tilting argument, using conditions which it is feasible to check. These results include a new formulation and proof of Skovgaard's theorem for the intensity of minimum contrast estimators, but under conditions which are typically straightforward to check in practice. Our most detailed application is to multivariate location-scatter models.     

Minimum contrast estimation of stationary processes based on the squared periodogram?

We present a class of minimum contrast estimators based on the objective function that is composed using the squared periodogram. We prove the consistency and asymptotic normality of the proposed estimators.     

Rates of convergence for minimum contrast estimators

Summary We shall present here a general study of minimum contrast estimators in a nonparametric setting (although our results are also valid in the classical parametric case) for independent observations. These estimators include many of the most popular estimators in various situations such as maximum likelihood estimators, least squares and other estimators of the regression function, estimators for mixture models or deconvolution... The main theorem relates the rate of convergence of those estimators to the entropy structure of the space of parameters. Optimal rates depending on entropy conditions are already known, at least for some of the models involved, and they agree with what we get for minimum contrast estimators as long as the entropy counts are not too large. But, under some circumstances (large entropies or changes in the entropy structure due to local perturbations), the resulting the rates are only suboptimal. Counterexamples are constructed which show that the phenomenon is real for non-parametric maximum likelihood or regression. This proves that, under purely metric assumptions, our theorem is optimal and that minimum contrast estimators happen to be suboptimal.     

Irregular trajectories in vakonomic mechanical systems

In his works, V.V. Kozlov proposed a mathematical model for the dynamics of a mechanical system with nonintegrable constraints, which was called vakonomic. In contrast to the then conventional nonholonomic model, trajectories in the vakonomic model satisfy necessary conditions for a minimum in a variational problem with equality constraints. We consider the so-called irregular case of this variational problem, which was not covered by Kozlov, when the trajectory is a singular point of the constraints and the necessary minimum conditions based on the Lagrange principle make no sense. This situation is studied using the theory of abnormal problems developed by the first author. As a result, the classical necessary minimum conditions are strengthened and developed to this class of problems.     

A simple method to compute economic order quantities

In this note, a simple method by using the arithmetic–geometric-mean-inequality theorem is proposed to computer the global minimum economic order quantities without taking complex differential calculus or using tedious algebraic manipulations. In contrast to (Minner, S., 2007. A note on how to compute economic order quantity without derivatives by cost comparisons. International Journal of Production Economics 105, 293–296; Wee, H.M., Wang, W.T., Chung, C.J., 2009. A modified method to computer economic order quantities without derivatives by cost-difference comparisons. European Journal of Operational Research) based on a local cost minimum initially to derive the solution and then proven it’s the global minimum, the proposed method yields the global minimum cost immediately and explicitly without using the cost comparisons and letting the time horizon to infinity.     

政府奖励与惩罚机制下闭环供应链网络均衡的互补模型

为研究政府经济政策对闭环供应链的影响,以非线性互补理论为基本工具,分别得到了在政府奖励机制与惩罚机制下,制造商负责回收的闭环供应链网络的各层均衡及整体均衡条件、经济解释及对应的非线性互补模型.最后通过数值算例验证了模型的正确性与有效性,其分析结果表明当政府预期的最低回收率较低时,惩罚机制优于奖励机制;当政府预期的最低回收率较高时,奖励机制优于惩罚机制.政府部门为了达到预期的最低回收率目标,可以适当调整奖励因子与惩罚因子.     

Triple-loop networks with arbitrarily many minimum distance diagrams

Minimum distance diagrams are a way to encode the diameter and routing information of multi-loop networks. For the widely studied case of double-loop networks, it is known that each network has at most two such diagrams and that they have a very definite form (“L-shape”).In contrast, in this paper we show that there are triple-loop networks with an arbitrarily big number of associated minimum distance diagrams. For doing this, we build-up on the relations between minimum distance diagrams and monomial ideals.     

New least-square algorithms

New algorithms are presented for approximating the minimum of the sum of squares ofM real and differentiable functions over anN-dimensional space. These algorithms update estimates for the location of a minimum after each one of the functions and its first derivatives are evaluated, in contrast with other least-square algorithms which evaluate allM functions and their derivatives at one point before using any of this information to make an update. These new algorithms give estimates which fluctuate about a minimum rather than converging to it. For many least-square problems, they give an adequate approximation for the solution more quickly than do other algorithms.It is a pleasure to thank J. Chesick of Haverford College for suggesting and implementing the application of this algorithm to x-ray crystallography.     

Statistical inference using higher-order information

This paper presents a class of minimum contrast estimators for stochastic processes with possible long-range dependence based on the information on higher-order spectral densities. The results on consistency and asymptotic normality of the proposed estimators are provided.     

Asymptotic distribution of minimum contrast estimators

We consider the behavior of minimum contrast estimators constructed from independent not identically distributed observations. It is proved under new assumptions that the consistent estimators are asymptotically normal. For the particular case of maximum likelihood estimators we generalize the known result of A. Philippou and G. Roussas.Translated from Statisticheskie Metody, pp. 56–65, 1980.     

Local extrema in genus-stratified graphs

Beyond the obvious organization of all the orientable imbeddings of a graph according to the genus of the imbedding surface, there are several seemingly natural ways to ascribe proximity of imbeddings. One of these is to stipulate that two imbeddings are adjacent if one imbedding can be obtained from the other by moving one end of an edge in its rotation. If one associates “altitude” with genus, then one might hope to construct algorithms for minimum genus and maximum genus by descent and ascent, respectively. This investigation of the structure of the system of orientable graph imbeddings reveals that although there may occur arbitrarily deep traps among the local minima, there cannot exist any strict local maxima. These new discoveries seem consistent with a known contrast in the computational complexity of the maximum genus and minimum genus problems. That is, whereas Furst, Gross, and McGeoch have devised a polynomial-time algorithm to find the maximum genus of an arbitrary graph, Thomassen has proved that the problem of finding the minimum genus is NP-complete.     

The maximum number of elementary particles in a super symmetric extension of the standard model

In a series of papers over the last few years El Naschie addressed the question of the minimum and maximum number of elementary particles which a mathematically consistent and a physically meaning full extended standard model should contain. El Naschie’s minimum is 62 particles namely 60 believed to have been already discovered in addition to one Higgs boson and one graviton which are theoretically needed but are not jet experimentally conformed. By contrast the maximum number of 69 particles is although consistent with many quantum field theories based models as well as a classical result by Dyson may not be the only possibility. In the present work we show that a larger number of 72 or even 84 particles are easily shown to be consistent with super string theory and super symmetry. Our work consists of two parts. The first part is a reappraisal of El Naschie’s results and the second is a derivation of the proposed possibility of an upper bound of 72 or 84 elementary particles.     

Estimating functions for noisy observations of ergodic diffusions

In this article, general estimating functions for ergodic diffusions sampled at high frequency with noisy observations are presented. The theory is formulated in terms of approximate martingale estimating functions based on local means of the observations, and simple conditions are given for rate optimality. The estimation of the diffusion parameter is faster than the estimation of the drift parameter, and the rate of convergence is classical for the drift parameter but not classical for the diffusion parameter. The link with specific minimum contrast estimators is established, as an example.     

On the existence of minimum contrast estimates in binary response model

When random samples are drawn from a 3-parameter distribution with a shifted origin and the observations corresponding to each sample are binary, criteria for the existence of minimum contrast estimates are given. These criteria can be drived by a method, called the probability contents boundary analysis. The probabilities of the existence of maximum likelihood estimates and least squares estimates are evaluated, by simulation with 1000 replications, in the case where the underlying distribution is a 3-parameter lognormal distribution or a 3-parameter loglogistic distribution.     

Extremal Problems in Logarithmic Potential Theory

We pose and solve an extremal problem of logarithmic potential theory that is dual to the main minimum problem in the theory of interior capacities of condensers but, in contrast to the latter, it is solvable even in the case of a nonclosed condenser. Its solution is a natural generalization of the classical notion of interior equilibrium measure of a set. A condenser is treated as a finite collection of signed sets such that the closures of sets with opposite signs are pairwise disjoint. We also prove several assertions on the continuity of extremals.     

A symmetric Roos bound for linear codes

The van Lint-Wilson AB-method yields a short proof of the Roos bound for the minimum distance of a cyclic code. We use the AB-method to obtain a different bound for the weights of a linear code. In contrast to the Roos bound, the role of the codes A and B in our bound is symmetric. We use the bound to prove the actual minimum distance for a class of dual BCH codes of length q²−1 over Fq. We give cyclic codes [63,38,16] and [65,40,16] over F₈ that are better than the known [63,38,15] and [65,40,15] codes.     

Generalized moment estimation of stochastic differential equations

We study the semiparametric estimation of stochastic differential equations employing methods based on moment conditions, comparing the finite sample and robustness properties of generalized method of moments, empirical likelihood and minimum contrast methods using unconditional and conditional formulations of moment conditions. The results obtained indicate that the estimators proposed, particularly, the estimators based on exponential tilting, obtain better results than those of the generalized methods of moments normally used to estimate stochastic differential equations. This conclusion is mainly derived from the robustness properties of this method in the presence of problems of incorrect specification.     

Statistics for Inhomogeneous Space-Time Shot-Noise Cox Processes

In the paper we introduce a flexible inhomogeneous space-time shot-noise Cox process model and derive a two-step estimation procedure for it. In the first step the inhomogeneity is estimated by means of a Poisson score estimating equation and in the second step we use minimum contrast estimation based on second order properties to obtain estimates of the clustering parameters. The suggested model is not separable but it has a special interaction structure which enables to use the spatial and temporal projections of the process for parameter estimation. Efficiency of the introduced method is investigated by means of a simulation study and it is compared to a previously used method.     

A short elementary proof of the Lagrange multiplier theorem

We present a short elementary proof of the Lagrange multiplier theorem for equality-constrained optimization. Most proofs in the literature rely on advanced analysis concepts such as the implicit function theorem, whereas elementary proofs tend to be long and involved. By contrast, our proof uses only basic facts from linear algebra, the definition of differentiability, the critical-point condition for unconstrained minima, and the fact that a continuous function attains its minimum over a closed ball.     

A high-dimensional Wilks phenomenon

A theorem by Wilks asserts that in smooth parametric density estimation the difference between the maximum likelihood and the likelihood of the sampling distribution converges toward a Chi-square distribution where the number of degrees of freedom coincides with the model dimension. This observation is at the core of some goodness-of-fit testing procedures and of some classical model selection methods. This paper describes a non-asymptotic version of the Wilks phenomenon in bounded contrast optimization procedures. Using concentration inequalities for general functions of independent random variables, it proves that in bounded contrast minimization (as for example in Statistical Learning Theory), the difference between the empirical risk of the minimizer of the true risk in the model and the minimum of the empirical risk (the excess empirical risk) satisfies a Bernstein-like inequality where the variance term reflects the dimension of the model and the scale term reflects the noise conditions. From a mathematical statistics viewpoint, the significance of this result comes from the recent observation that when using model selection via penalization, the excess empirical risk represents a minimum penalty if non-asymptotic guarantees concerning prediction error are to be provided. From the perspective of empirical process theory, this paper describes a concentration inequality for the supremum of a bounded non-centered (actually non-positive) empirical process. Combining the now classical analysis of M-estimation (building on Talagrand??s inequality for suprema of empirical processes) and versatile moment inequalities for functions of independent random variables, this paper develops a genuine Bernstein-like inequality that seems beyond the reach of traditional tools.