𝔖 Bobbio Scriptorium
✦   LIBER   ✦

A note on filtering for long memory processes

✍ Scribed by A. Thavaneswaran; C.C. Heyde

Publisher
Elsevier Science
Year
2001
Tongue
English
Weight
425 KB
Volume
34
Category
Article
ISSN
0895-7177

No coin nor oath required. For personal study only.

✦ Synopsis

This paper illustrates the use of quasilikelihood methods of inference for a class of possibly long-memory processes such as H-sssi (self-similar stationary increments) processes and long-range dependent sequences.

In particular, they can be used in a general derivation without assuming normality of the process; this extends the result of Gripenberg filtering for models with linear intensity is also discussed in some detail. Ltd. All rights rese'rved.

πŸ“œ SIMILAR VOLUMES

Multi-step forecasting for long-memory p
Multi-step forecasting for long-memory processes
✍ Julia Brodsky; Clifford M. Hurvich πŸ“‚ Article πŸ“… 1999 πŸ› John Wiley and Sons 🌐 English βš– 298 KB

In this paper we present results of a simulation study to assess and compare the accuracy of forecasting techniques for long-memory processes in small sample sizes. We analyse dierences between adaptive ARMA(1,1) L-step forecasts, where the parameters are estimated by minimizing the sum of squares o

A note on filtering electrocardiograms
A note on filtering electrocardiograms
✍ T. Allan Pryor πŸ“‚ Article πŸ“… 1971 πŸ› Elsevier Science 🌐 English βš– 224 KB

In developing computer programs for analysis of the electrocardiogram, concern for noise superimposed on the signal is essential. The two major sources of noise are 60 cycle pickup and random myoelectric noise. A large portion of this noise can be suppressed by low pass filtering of the signal. Desi

A note on the memory length of optimal n
A note on the memory length of optimal nonlinear filters
✍ Rami Atar; Ofer Zeitouni πŸ“‚ Article πŸ“… 1998 πŸ› Elsevier Science 🌐 English βš– 86 KB

Consider the one-dimensional ΓΏltering problem with state di usion coe cient and observation noise coe cient 1-, where 1 2 Β‘ Β‘1 is ΓΏxed. In the regime β†’ 0, we provide an example of state dynamics and a corresponding asymptotically optimal ΓΏlter whose memory length is short in a strong sense. This sta

Martingale transforms and Girsanov theor
Martingale transforms and Girsanov theorem for long-memory Gaussian processes
✍ Yuliya Mishura; Esko Valkeila πŸ“‚ Article πŸ“… 2001 πŸ› Elsevier Science 🌐 English βš– 134 KB

The long-memory Gaussian processes presented as the integrals Vt = t 0 h(t -s)'(s) dWs and Bt = t 0 (s) dVs are considered. The fractional Brownian motion is a particular case when '; ; h are the power functions. The integrals Vt are transformed into Gaussian martingales. The Girsanov theorem for Bt