Autoregressive conditional heteroskedasticity and changes in regime

Hamilton, James D.; Susmel, Raúl

doi:10.1016/0304-4076(94)90067-1

Cited by 1,505 publications

(1,109 citation statements)

References 27 publications

Supporting

Mentioning

1,050

Contrasting

Unclassified

Order By: Relevance

“…After all, if the low-variance regime is also the low-persistence regime, the large shock will be out of the market very soon after the switch to the low-variance regime. In this respect, our model generalizes the models in Hamilton and Susmel (1994) and Cai (1994), as their regime variances only differ by a multiplicative or additive constant, respectively, not by differences in the ARCH parameters.…”

Section: Flexibility Regarding Volatility Persistencementioning

confidence: 61%

“…The ARCH(0;0) model has zero ARCH terms, so constant variance, in both regimes, as in Dewachter (1997) and Scheicher (1999); this model is used to analyze the effect of introducing only regimes. The other ARCH-type model, ARCH(Q 1 ;4) with Q 1 determined below, is in the spirit of Cai (1994) and Hamilton and Susmel (1994). It is, however, somewhat more general in the sense that the regime-specific ARCH models are allowed to vary across regime in an unrestricted way, whereas in Cai (1994) and Hamilton and Susmel (1994) the difference between the low-and high-variance regime ARCH models is just an additive or multiplicative constant, respectively.…”

Section: Estimation Resultsmentioning

confidence: 99%

“…Since V t−1 {ε t | e r t } then only depends on the current regime r t , there is no problem of path dependence. (More precisely, Cai (1994) and Hamilton and Susmel (1994) use slightly different models in which V t−1 {ε t | e r t } not only depends on the current but also on a few recent regimes. The essential point is that the conditional variance depends only on a small number of regimes, which can be integrated out in the likelihood quite easily.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Improving GARCH volatility forecasts with regime-switching GARCH

Klaassen

2002

Advances in Markov-Switching Models

View full text Add to dashboard Cite

Many researchers use GARCH models to generate volatility forecasts. Using data on three major U.S. dollar exchange rates we show that such forecasts are too high in volatile periods. We argue that this is due to the high persistence of shocks in GARCH forecasts. To obtain more flexibility regarding volatility persistence, this paper generalizes the GARCH model by distinguishing two regimes with different volatility levels; GARCH effects are allowed within each regime. The resulting Markov regime-switching GARCH model improves on existing variants, for instance by making multi-periodahead volatility forecasting a convenient recursive procedure. The empirical analysis demonstrates that the model resolves the problem with the high single-regime GARCH forecasts and that it yields significantly better outof-sample volatility forecasts.Key words: GARCH, Markov-switching, variance, forecasting, exchange rates. JEL classification: C52, C53, F31. * Department of Economics, University of Amsterdam, Roetersstraat 11, 1018 WB Amsterdam, the Netherlands; tel: +31-20-5254191; fax: +31-20-5254254; E-mail: klaassen@fee.uva.nl. I thank Harry Huizinga, Frank de Jong, Michael McAleer, Bertrand Melenberg, Theo Nijman, Arthur van Soest, Kenneth West, the editors of this issue, James Hamilton and Baldev Raj, and two referees for very useful and constructive comments.

show abstract

Section: Flexibility Regarding Volatility Persistencementioning

confidence: 61%

Section: Estimation Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Improving GARCH volatility forecasts with regime-switching GARCH

Klaassen

2002

Advances in Markov-Switching Models

View full text Add to dashboard Cite

show abstract

“…These models are an alternative way of modelling volatility processes that contains breaks. Hamilton and Susmel (1994) argued that very large shocks, such as the one a¤ecting the stocks in October 1987, may have consequences for subsequent volatility so di¤erent from consequences of small shocks that a standard ARCH or GARCH model cannot describe them properly. Their Markovswitching ARCH model is de…ned as follows:…”

Section: Markov-switching Arch and Garchmentioning

confidence: 99%

An Introduction to Univariate GARCH Models

Teräsvirta

2009

Handbook of Financial Time Series

105

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in EconStor may

show abstract

“…Nesta linha, os modelos GARCH foram expandidos e generalizados em várias direções: por exemplo, o GARCH exponencial [de Nelson (1991)], o de limiar [Zakoian (1991)], a generalização de Hentschel (1995) que aninha vários modelos em uma só especificação, e os modelos com parâmetros variáveis no tempo de acordo com processos de Markov [Hamilton & Susmel (1994) Issler (1999), que compara os resultados obtidos usando modelos da família GARCH em séries de retornos de ativos de diferentes tipos (ação, bônus, moeda e commodity); por Pereira, Hotta, Souza & Almeida (1999), que comparam modelos da família GARCH, volatilidade estocástica e GARCH com parâmetros variantes no tempo, usando três das quatro séries usadas por Issler (1999).…”

Section: Referênciasunclassified

Propriedades Estatísticas Das Séries De Retornos Das Principais Ações Brasileiras

Costa

Baidya

2001

Pesqui. Oper.

View full text Add to dashboard Cite

ResumoO artigo analisa seis séries de retornos, escolhidas entre as mais líquidas do mercado e de setores diferentes da economia. São estudadas a estacionariedade, a distribuição incondicional e a independência; de maneira geral as séries podem ser consideradas estacionárias, com distribuição não normal (leptocúrtica) e dependentes no tempo. A estacionariedade é analisada através do teste ADF, através dos coeficientes de modelos GARCH ajustados aos dados, pelos coeficientes de bicorrelação e com o uso de regressão localmente ponderada. A normalidade é rejeitada pelo teste de Jarque e Bera. A dependência (linear e não linear) é constatada pelas autocorrelações dos retornos e dos seus quadrados: tenta-se modelar a dependência com modelos ARMA, de amortecimento exponencial e GARCH mas os resíduos dos modelos, testados pelo teste BDS, mostram que nenhum deles representa bem o processo gerador dos dados. Palavras-chave: séries financeiras, estacionariedade, independência. AbstractThis paper studies the returns of six Brazilian stocks, chosen among the most liquid and from different economic sectors. Stationarity, unconditional distribution and independence are studied, and the conclusion is that the series are stationary, have non-normal (leptokurtic) distribution and are dependent. Stationarity is studied with the help of the ADF test, of the coefficients of GARCH models adjusted to the data, of bicorrelation coefficients and of locally weighted regression. Normality was rejectec using the Jarque and Bera test. Dependence (linear and non-linear) was indicated by the autocorrelations of returns and squared returns: ARMA, exponential smoothing, and GARCH models are used to try to capture the dependence, but the BDS tests of the model's residuals show that they do not represent well the data generating process.

show abstract

Autoregressive conditional heteroskedasticity and changes in regime

Cited by 1,505 publications

References 27 publications

Improving GARCH volatility forecasts with regime-switching GARCH

Improving GARCH volatility forecasts with regime-switching GARCH

An Introduction to Univariate GARCH Models

Propriedades Estatísticas Das Séries De Retornos Das Principais Ações Brasileiras

Contact Info

Product

Resources

About