ARCH Models and Financial Applications (Springer Series in Statistics) - Hardcover

Gourieroux, Christian

Hardcover

ISBN 10: 0387948767 ISBN 13: 9780387948768

Publisher: Springer, 1997

Synopsis

1.1 The DevelopmentofARCH Models Time series models have been initially introduced either for descriptive purposes like prediction and seasonal correction or for dynamic control. In the 1970s, the researchfocusedonaspecificclassoftimeseriesmodels,theso-calledautoregres­ sive moving average processes (ARMA), which were very easy to implement. In thesemodels,thecurrentvalueoftheseriesofinterestiswrittenasalinearfunction ofits own laggedvalues andcurrentandpastvaluesofsomenoiseprocess, which can be interpreted as innovations to the system. However, this approach has two major drawbacks: 1) it is essentially a linear setup, which automatically restricts the type of dynamics to be approximated; 2) it is generally applied without im­ posing a priori constraintson the autoregressive and moving average parameters, which is inadequatefor structural interpretations. Among the field ofapplications where standard ARMA fit is poorare financial and monetary problems. The financial time series features various forms ofnon­ lineardynamics,the crucialone being the strongdependenceofthe instantaneous variabilityoftheseriesonitsownpast. Moreover,financial theoriesbasedoncon­ ceptslikeequilibriumorrationalbehavioroftheinvestorswouldnaturallysuggest including and testing some structural constraints on the parameters. In this con­ text, ARCH (Autoregressive Conditionally Heteroscedastic) models, introduced by Engle (1982), arise as an appropriate framework for studying these problems. Currently, there existmorethan onehundredpapers and some dozenPh.D. theses on this topic, which reflects the importance ofthis approach for statistical theory, finance and empirical work. 2 1. Introduction From the viewpoint ofstatistical theory, the ARCH models may be considered as some specific nonlinear time series models, which allow for aquite exhaustive studyoftheunderlyingdynamics.Itisthereforepossibletoreexamineanumberof classicalquestions like the random walkhypothesis, prediction intervals building, presenceoflatentvariables [factors] etc., and to test the validity ofthe previously established results.

About this title

Review

From the reviews:

RISKBOOK.COM

"Gourieroux offers a nice balance of theory and application in this book on ARCH modeling in finance...The book is well written and has extensive references. Its focus on finance will appeal to financial engineers and financial risk managers."

Synopsis

The classical ARMA models have limitations when applied to the field of financial and monetary economics. Financial time series present nonlinear dynamic characteristics and the ARCH models offer a more adaptive framework for this type of problem. This book surveys the recent work in this area from the perspective of statistical theory, financial models, and applications and will be of interest to theorists and practitioners. From the view point of statistical theory, ARCH models may be considered as specific nonlinear time series models which allow for an exhaustive study of the underlying dynamics. It is possible to reexamine a number of classical questions such as the random walk hypothesis, prediction interval building, presence of latent variables etc., and to test the validity of the previously studied results. There are two main categories of potential applications. One is testing several economic or financial theories concerning the stocks, bonds, and currencies markets, or studying the links between the short and long run.

The second is related to the interventions of the banks on the markets, such as choice of optimal portfolios, hedging portfolios, values at risk, and the size and times of block trading.

Edition details

• Publisher: Springer
• Publication date: 1997
• Language: English
• ISBN 10: 0387948767
• ISBN 13: 9780387948768
• Binding: Hardcover
• Number of pages: 238