An autoregressive model based on the generalized hyperbolic distribution

Tutkimustuotos: ArtikkelijulkaisuArtikkeliTieteellinenvertaisarvioitu

Kuvaus

Abstract We define a non-linear autoregressive time series model based on the generalized hyperbolic distribution in an attempt to model time series with non-Gaussian features such as skewness and heavy tails. We show that the resulting process has a simple condition for stationarity and it is also ergodic. An empirical example with a forecasting experiment is presented to illustrate the features of the proposed model. This article is protected by copyright. All rights reserved.
Alkuperäiskielienglanti
LehtiScandinavian Journal of Statistics
ISSN0303-6898
DOI - pysyväislinkit
TilaJulkaistu - 29 lokakuuta 2019
OKM-julkaisutyyppiA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä, vertaisarvioitu

Tieteenalat

  • 112 Tilastotiede

Lainaa tätä

@article{453e9ca4108f443e8518674c84bdbd24,
title = "An autoregressive model based on the generalized hyperbolic distribution",
abstract = "Abstract We define a non-linear autoregressive time series model based on the generalized hyperbolic distribution in an attempt to model time series with non-Gaussian features such as skewness and heavy tails. We show that the resulting process has a simple condition for stationarity and it is also ergodic. An empirical example with a forecasting experiment is presented to illustrate the features of the proposed model. This article is protected by copyright. All rights reserved.",
keywords = "Autoregressive model, conditional heteroscedasticity, generalized hyperbolic distribution, non-linear time series, skewness, 112 Statistics and probability",
author = "Henri Karttunen",
year = "2019",
month = "10",
day = "29",
doi = "10.1111/sjos.12427",
language = "English",
journal = "Scandinavian Journal of Statistics",
issn = "0303-6898",
publisher = "Wiley",

}

An autoregressive model based on the generalized hyperbolic distribution. / Karttunen, Henri.

julkaisussa: Scandinavian Journal of Statistics, 29.10.2019.

Tutkimustuotos: ArtikkelijulkaisuArtikkeliTieteellinenvertaisarvioitu

TY - JOUR

T1 - An autoregressive model based on the generalized hyperbolic distribution

AU - Karttunen, Henri

PY - 2019/10/29

Y1 - 2019/10/29

N2 - Abstract We define a non-linear autoregressive time series model based on the generalized hyperbolic distribution in an attempt to model time series with non-Gaussian features such as skewness and heavy tails. We show that the resulting process has a simple condition for stationarity and it is also ergodic. An empirical example with a forecasting experiment is presented to illustrate the features of the proposed model. This article is protected by copyright. All rights reserved.

AB - Abstract We define a non-linear autoregressive time series model based on the generalized hyperbolic distribution in an attempt to model time series with non-Gaussian features such as skewness and heavy tails. We show that the resulting process has a simple condition for stationarity and it is also ergodic. An empirical example with a forecasting experiment is presented to illustrate the features of the proposed model. This article is protected by copyright. All rights reserved.

KW - Autoregressive model

KW - conditional heteroscedasticity

KW - generalized hyperbolic distribution

KW - non-linear time series

KW - skewness

KW - 112 Statistics and probability

U2 - 10.1111/sjos.12427

DO - 10.1111/sjos.12427

M3 - Article

JO - Scandinavian Journal of Statistics

JF - Scandinavian Journal of Statistics

SN - 0303-6898

ER -