Results 91 to 100 of about 361,494 (239)
Multiple Changepoint Detection for Non‐Gaussian Time Series
Journal of Time Series Analysis, EarlyView.ABSTRACT This article combines methods from existing techniques to identify multiple changepoints in non‐Gaussian autocorrelated time series. A transformation is used to convert a Gaussian series into a non‐Gaussian series, enabling penalized likelihood methods to handle non‐Gaussian scenarios.
Robert Lund +3 more
wiley +1 more source
Some Algorithms for the Conditional Mean Vector and Covariance Matrix [PDF]
We consider here the problem of computing the mean vector and covariance matrix for a conditional normal distribution, considering especially a sequence of problems where the conditioning variables are changing.
John F. Monahan
core +1 more source
Independent Process Analysis without A Priori Dimensional Information [PDF]
, 2007 Recently, several algorithms have been proposed for independent subspace analysis where hidden variables are i.i.d. processes. We show that these methods can be extended to certain AR, MA, ARMA and ARIMA tasks. Central to our paper is that we introduce a
Kiszlinger, Melinda +3 more
core +2 more sources
Inconsistencies in the application of harmonic analysis to pulsating stars
, 2015 Using ultra-precise data from space instrumentation we found that the underlying functions of stellar light curves from some AF pul- sating stars are non-analytic, and consequently their Fourier expansion is not guaranteed.
Garrido, R. +2 more
core +1 more source
Estimació dels paràmetres de models ARMA (P,Q) mitjançant algorismes de filtratge òptim
, 2023 El objetivo del trabajo era sintetizar un filtro no lineal optimo para la estimación de parámetros de modelos arma. El interés de un filtro de este estilo reside en elhecho que permite evaluar exactamente el numero mínimo deobservaciones necesarias para realizar una estimación conuna determinada precisión.A lo largo del trabajo se analizan ypresentan ...
openaire +4 more sources
Automated Bandwidth Selection for Inference in Linear Models With Time‐Varying Coefficients
Journal of Time Series Analysis, EarlyView.ABSTRACT The problem of selecting the smoothing parameter, or bandwidth, for kernel‐based estimators of time‐varying coefficients in linear models with possibly endogenous explanatory variables is considered. We examine automated bandwidth selection by means of cross‐validation, a nonparametric variant of Akaike's information criterion, and bootstrap ...
Charisios Grivas, Zacharias Psaradakis
wiley +1 more source
Lecturas de Economía, 2013 Prueba de hipótesis sobre la existencia de una raíz fraccional en una serie de tiempo no estacionaria Resumen: En este trabajo se propone una modificación de la prueba de hipótesis propuesta por Castaño, Gómez y Gallón (2008) para determinar la ...
Diego Lemus, Elkin Castaño
doaj +1 more source
Online Detection of Forecast Model Inadequacies Using Forecast Errors
Journal of Time Series Analysis, EarlyView.ABSTRACT In many organizations, accurate forecasts are essential for making informed decisions in a variety of applications, from inventory management to staffing optimization. Whatever forecasting model is used, changes in the underlying process can lead to inaccurate forecasts, which will be damaging to decision‐making.
Thomas Grundy +2 more
wiley +1 more source
Tropical and Subtropical Agroecosystems, 2013 El objetivo fue aplicar un modelo de series de tiempo univariado tipo ARIMA en la descripción y pronóstico del comportamiento de la producción lechera de bovino en el estado, aplicando para ello la metodologÃa de Box y Jenkins.
Eduardo Sánchez +4 more
doaj
Moments of the ARMA-EGARCH Model [PDF]
This paper considers the moment structure of the ARMA(r,s)-EGARCH(p,q) model. In particular, we provide the autocorrelation function and any arbitrary moment of the conditional variance/squared errors.
J. Kim, Menelaos Karanasos
core