Trimming frequencies in log-periodogram regression of long memory time seriesReport as inadecuate




Trimming frequencies in log-periodogram regression of long memory time series - Download this document for free, or read online. Document in PDF available to download.

Editor: Universidad Carlos III de Madrid. Departamento de Estadística

Issued date: 1996-03

Serie-No.: UC3M Working papers. Statistics and Econometrics96-14

Keywords: Autocorrelation function , Fractional ARIMA models

Rights: Atribución-NoComercial-SinDerivadas 3.0 España

Abstract:Previous work on log-periodogram regression in time series with long range dependence is reviewed. The effect of both low and large frequencies on the estimate of the fractional difference parameter is analyzed. Some new simulation results are presented.Previous work on log-periodogram regression in time series with long range dependence is reviewed. The effect of both low and large frequencies on the estimate of the fractional difference parameter is analyzed. Some new simulation results are presented.+-





Author: Martínez, Cristina; Velilla, Santiago

Source: http://e-archivo.uc3m.es


Teaser



Universidad Carlos III de Madrid Repositorio institucional e-Archivo http:--e-archivo.uc3m.es Departamento de Estadística DES - Working Papers.
Statistics and Econometrics.
WS 1996-03 Trimming frequencies in log-periodogram regression of long memory time series Martínez, Cristina http:--hdl.handle.net-10016-10428 Descargado de e-Archivo, repositorio institucional de la Universidad Carlos III de Madrid TRIMMING FREQUENCIES IN LOG-PERIODOGRAM REGRESSION OF LONG-MEMORY TIME SERIES Cristina Martinez and Santiago Velilla 96-14 C-) a::: UJ 0. « 0. Universidad Carlos III de Madrid Working Paper 96-14 Departamento de Estadfstica y Econometrfa Statistics and Econometrics Series 04 March 1996 Universidad Carlos III de Madrid Calle Madrid, 126 28903 Getafe (Spain) Fax (341) 624-9849 TRIMMING FREQUENCIES IN LOG-PERIODOGRAM REGRESSION OF LONG-MEMORY TIME SERIES Cristina Martfnez and Santiago Velilla* Abstract _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ __ Previous work on log-periodogram regression in time series with long range dependence is reviewed.
The effect of both low and large frequencies on the estimate of the fractional difference parameter is analyzed.
Some new simulation results are presented. Key Words Autocorrelation function; Fractional ARIMA models; Spectral density. * Departamento de Estadfstica y Econometrfa, Universidad Carlos III de Madrid.
Research partially supported by grant PB-930232 (Spain). 1. INTRODUCTION There is strong evidence that long - memory time series occur quite frequently in practice.
A characteristic indication of long range dependence is the appearance of unbounded spectral densities in a neighborhood of the = o. origin i-. The class of fractional ARIMA(p,d,q) models allow for this situation.
This paper treats some aspects of estimation of the parameter d. Some background is given in section 2, where notation is also established. Log - periodogram regression, a fundamental techni...





Related documents