In vector autoregressive modeling, the order selected with the Akaike Information Criterion tends to be too high. This effect is called overfit. Finite sample effects are an important cause of overfit. By incorporating finite sample effects, an order selection criterion for vector AR models can be found with an optimal trade-off of underfit and overfit. The finite sample formulae in this paper ...

With an optimal design one wants to determine the ideal allocation of observations for the estimation of the unknown parameter vector θ of a given model ( ) ( ) θ ; i i x f y E = , with [ ] p T θ θ θ L 1 = , ( ) n T x x X ,..., 1 = , the xi from a given experimental region ER.. Let ( ) X V ; θ be the asymptotical variance-covariance matrix of the least squares estimatorθ̂ of θ . We consider the ...

Objective. The aim of this article is to develop a program for approximate estimation regression models specified on the basis Leontief production function (non-elementary regressions with two variables) and use it modeling unemployment rate in Irkutsk region. Method . Estimation non-elementary carried out using ordinary least squares method. To find estimates, we used previously developed algo...

Support Vector Machine(SVM) is a powerful classifier used successfully in many pattern recognition problems. Furthermore, the good performance of SVM classifier has been shown in handwriting recognition field. Least Squares SVM, like SVM, is based on the marginmaximization principle performing structural risk, but its training is easier: it is only needed to solve a convex linear problem rather...

The paper presents a general framework for the Frisch scheme and the extended compensated least squares technique within which two new algorithms for the identification of single-input single-output linear time-invariant errors-in-variables models are proposed. The first algorithm is essentially the Frisch scheme using a novel model selection criterion. The second method is a modification of th...

This paper addresses the problems of learning from labelled data contextual discounting and contextual reinforcement, two correction schemes recently introduced in belief function theory. It shows that given a particular error criterion based on the plausibility function, for each of these two contextual correction schemes, there exists an optimal set of contexts that ensures the minimization o...

The aim of this paper is to compare through Monte Carlo simulations the finite sample properties of the estimates of the parameters of the weighted exponential distribution obtained by five estimation methods: maximum likelihood, moments, L-moments, ordinary least-squares, and weighted least-squares. The bias and mean-squared error are used as the criterion for comparison. The simulation study ...

I show several types of topological biases in distance-based methods that use the least-squares method to evaluate branch lengths and the minimum evolution (ME) or the Fitch-Margoliash (FM) criterion to choose the best tree. For a 6-species tree, there are two tree shapes, one with three cherries (a cherry is a pair of adjacent leaves descending from the most recent common ancestor), and the ot...

This paper is concerned with regression under a “sum” of partial order constraints. Examples include locally monotonic, piecewise monotonic, runlength constrained, and unimodal and oligomodal regression. These are of interest not only in nonlinear filtering but also in density estimation and chromatographic analysis. It is shown that under a least absolute error criterion, these problems can be...