Home  About us  Contact
 

Local Versions (local + version)

Distribution by Scientific Domains
Mathematics and Statistics50%

Selected Abstracts

Model Selection for Broadband Semiparametric Estimation of Long Memory in Time Series

JOURNAL OF TIME SERIES ANALYSIS, Issue 6 2001
Clifford M. Hurvich
We study the properties of Mallows' CL criterion for selecting a fractional exponential (FEXP) model for a Gaussian long-memory time series. The aim is to minimize the mean squared error of a corresponding regression estimator dFEXP of the memory parameter, d. Under conditions which do not require that the data were actually generated by a FEXP model, it is known that the mean squared error MSE=E[dFEXP,d]2 can converge to zero as fast as (log n)/n, where n is the sample size, assuming that the number of parameters grows slowly with n in a deterministic fashion. Here, we suppose that the number of parameters in the FEXP model is chosen so as to minimize a local version of CL, restricted to frequencies in a neighborhood of zero. We show that, under appropriate conditions, the expected value of the local CL is asymptotically equivalent to MSE. A combination of theoretical and simulation results give guidance as to the choice of the degree of locality in CL. [source]

Identification in Nonseparable Models

ECONOMETRICA, Issue 5 2003
Andrew Chesher
Weak nonparametric restrictions are developed, sufficient to identify the values of derivatives of structural functions in which latent random variables are nonseparable. These derivatives can exhibit stochastic variation. In a microeconometric context this allows the impact of a policy intervention, as measured by the value of a structural derivative, to vary across people who are identical as measured by covariates. When the restrictions are satisfied quantiles of the distribution of a policy impact across people can be identified. The identification restrictions are local in the sense that they are specific to the values of the covariates and the specific quantiles of latent variables at which identification is sought. The conditions do not include the commonly required independence of latent variables and covariates. They include local versions of the classical rank and order conditions and local quantile insensitivity conditions. Values of structural derivatives are identified by functionals of quantile regression functions and can be estimated using the same functionals applied to estimated quantile regression functions. [source]

Application of local and global particle swarm optimization algorithms to optimal design and operation of irrigation pumping systems,

IRRIGATION AND DRAINAGE, Issue 3 2009
M. H. Afshar
stations de pompage; conception et exploitation; optimisation par essaims particulaires locale et globale Abstract A particle swarm optimization (PSO) algorithm is used in this paper for optimal design and operation of irrigation pumping systems. An irrigation pumping systems design and management model is first introduced and subsequently solved with the newly introduced PSO algorithm. The solution of the model is carried out in two steps. In the first step an exhaustive enumeration is carried out to find all feasible sets of pump combinations able to cope with a given demand curve over the required period. The PSO algorithm is then called in to search for optimal operation of each set. Having solved the operation problem of all feasible sets, the total cost of operation and depreciation of initial investment is calculated for all the sets and the optimal set and the corresponding optimal operating policy is determined. The proposed model is applied to the design and operation of a real-world irrigation pumping system and the results are presented and compared with those of a genetic algorithm. Two global and local versions of the PSO algorithm are used and their efficiencies are compared to each other and that of a genetic algorithm (GA) model. The results indicate that the proposed model in conjunction with the PSO algorithm is a versatile management model for the design and operation of real-world irrigation pumping systems. Copyright © 2008 John Wiley & Sons, Ltd. Un algorithme d'optimisation par essaims particulaires (PSO en anglais) est employé dans cet article pour la conception et l'exploitation optimale des systèmes d'irrigation avec pompages. Un modèle de conception et de gestion du système est d'abord présenté et ensuite résolu avec le nouvel algorithme PSO. La solution du modèle est effectuée dans deux étapes. Dans la première étape une énumération exhaustive est effectuée pour trouver toutes les combinaisons possibles de pompes capables de répondre à une courbe de demande donnée pendant la période souhaitée. L'algorithme d'optimisation par essaims particulaires est alors utilisé pour rechercher la gestion optimale de chaque ensemble. Ayant résolu le problème de gestion de toutes les combinaisons possibles, le coût d'exploitation et d'amortissement de l'investissement initial est calculé pour chacune et la combinaison optimale et sa stratégie de gestion optimale est déterminée. Le modèle proposé est appliqué à la conception et l'exploitation d'un système irrigué réel et les résultats sont présentés et comparés à ceux d'un algorithme génétique. Deux versions globales et locales de l'algorithme PSO sont employées et leurs efficacités sont comparées entre eux et avec celles d'un modèle à algorithme génétique. Les résultats indiquent que le modèle proposé associé à l'algorithme d'optimisation par essaims particulaires est un modèle souple pour la conception et l'exploitation systèmes irrigués réels avec pompage. Copyright © 2008 John Wiley & Sons, Ltd. [source]

Sharp local embedding inequalities

COMMUNICATIONS ON PURE & APPLIED MATHEMATICS, Issue 1 2006
Junfang Li
In this paper we establish local versions of the Onofri and sharp Sobolev inequalities. Such local inequalities enable us to give a more direct and simpler proof of the Onofri inequality on ,,2, as well as an alternative proof of sharp Sobolev inequalities on ,,n (for n , 3). © 2005 Wiley Periodicals, Inc. [source]