Glossary to ARCH (GARCH

Tim Bollerslev Duke University CREATES and NBER First Version: June 25, 2007 This Version: February 16, 2009

This paper was prepared for Volatility and Time Series Econometrics: Essays in Honour of Robert F. Engle (eds. Tim Bollerslev, Jeffrey R. Russell and Mark Watson), Oxford University Press, Oxford, UK. I would like to acknowledge the financial support provided by a grant from the NSF to the NBER and CREATES funded by the Danish National Research Foundation. I would also like to thank Frank Diebold, Xin Huang, Andrew Patton, Neil Shephard and Natalia Sizova for valuable comments and suggestions. Of course, I am solely to blame for any errors or omissions.

Abstract: This paper provides an encyclopedic type reference guide to the long list of ARCH acronyms that have been used in the literature. In addition to the acronyms association with specific parametric models, I have also included descriptions of abbreviations association with more general procedures and ideas that figure especially prominently in the ARCH literature. With a few exceptions, I have restricted the list of acronyms to those which have appeared in already published studies. Keywords: ARCH, GARCH, ARCH-M, EGARCH, IGARCH, BEKK, CCC, DCC.


Preface: Rob Engle’s seminal Nobel Prize winning 1982 Econometrica article on the AutoRegressive Conditional Heteroskedastic (ARCH) class of models spurred a virtual “arms race” into the development of new and better procedures for modeling and forecasting time-varying financial market volatility. Some of the most influential of these early papers were collected in Engle (1995). Numerous surveys of the burgeon ARCH literature also exist; e.g., Andersen and Bollerslev (1998), Andersen, Bollerslev, Christoffersen and Diebold (2006), Bauwens, Laurent and Rombouts (2006), Bera and Higgins (1993), Bollerslev, Chou and Kroner (1992), Bollerslev, Engle and Nelson (1994), Degiannakis and Xekalaki (2004), Diebold (2004), Diebold and Lopez (1995), Engle (2001, 2004), Engle and Patton (2001), Pagan (1996), Palm (1996), and Shephard (1996). Moreover, ARCH models have now become standard textbook material in econometrics and finance as exemplified by, e.g., Alexander (2001, 2008), Brooks (2002), Campbell, Lo and MacKinlay (1997), Chan (2002), Christoffersen (2003), Enders (2004), Franses and van Dijk (2000), Gourieroux and Jasiak (2001), Hamilton (1994), Mills (1993), Poon (2005), Singleton (2006), Stock and Watson (2005), Tsay (2002), and Taylor (2004). So, why another survey type paper? Even a cursory glance at the many reviews and textbook treatments cited above reveals a perplexing “alphabet-soup” of acronyms and abbreviations used to describe the plethora of models and procedures that have been developed over the years. Hence, as a complement to these more traditional surveys, I have tried to provide an alternative and easy-to-use encyclopedic type reference guide to the long list of ARCH acronyms. Comparing the length of this list to the list of general Acronyms in Time Series Analysis (ATSA) compiled by Granger (1983) further underscores the scope of the research efforts and new developments that have occurred in the area following the introduction of the basic linear ARCH model in Engle (1982). My definition of what constitutes an ARCH acronym is, of course, somewhat arbitrary and subjective. In addition to the obvious cases of acronyms association with specific parametric models, I have also included descriptions of some abbreviations association with more general procedures and ideas that figure especially prominently in the ARCH literature. With a few exceptions, I have restricted the list of acronyms to those which have appeared in already published studies. Following Granger (1983), I have purposely not included the names of specific computer programs or procedures, as these are often of limited availability and may also be sold commercially. Even though I have tried my best to be as comprehensive and inclusive as possible, I have almost surely omitted some abbreviations. To everyone responsible for an acronym that I have inadvertently left out, please accept my apology. Lastly, let me make it clear that the mere compilation of this list does not mean that I endorse the practice of associating each and every ARCH formulation with it’s own unique acronym. In fact, the sheer length of this list arguably suggests that the use of special names and abbreviations originally intended for easily telling different ARCH models apart might have reached a point of diminishing returns to scale. ii

AARCH (Augmented ARCH) The AARCH model of Bera, Higgins and Lee (1992) extends the linear ARCH(q) model (see ARCH) to allow the conditional variance to depend on crossproducts of the lagged innovations. Defining the q×1 vector , the AARCH(q) model may be expressed as: , where A denotes a q×q symmetric positive definite matrix. If A is diagonal, the model reduces to the standard linear ARCH(q) model. The Generalized AARCH, or GAARCH model is obtained by including lagged conditional variances on the right-hand-side of the equation. The slightly more general GQARCH representation was proposed independently by Sentana (1995) (see GQARCH). ACD (Autoregressive Conditional Duration) The ACD model of Engle and Russell (1998) was developed to describe dynamic dependencies in the durations between randomly occurring events. The model has found especially wide use in the analysis of high-frequency financial data and times between trades or quotes. Let denote the time interval between the ith and the (i-1)th event. The popular ACD(1,1) model then parameterizes the expected durations, , analogous to the conditional variance in the GARCH(1,1) model (see GARCH), . Higher order ACD(p,q) models are defined in a similar manner. Quasi Maximum Likelihood Estimates (see QMLE) of the parameters in the ACD(p,q) model may be obtained by applying standard GARCH(p,q) estimation procedures to , with the conditional mean fixed at zero (see also ACH and MEM). ACH1 (Autoregessive Conditional Hazard) The ACH model of Hamilton and Jordá (2002) is designed to capture dynamic dependencies in hazard rates, or the probability for the occurrence of specific events. The basic ACH(p,q) model without any updating of the expected hazard rates between events is asymptotically equivalent to the ACD(p,q) model for the times between events (see ACD). ACH2 (Adaptive Conditional Heteroskedasticity) In parallel to the idea of allowing for timevarying variances in a sequence of normal distributions underlying the basic ARCH model (see ARCH), it is possible to allow the scale parameter in a sequence of Stable Paretian distributions to change over time. The ACH formulation for the scale parameter, , first proposed by McCulluch (1985) postulates that the temporal variation may be described by an exponentially weighted moving average (see EWMA) of the form, -1-

The ACM and ACD models (see ACD) may be combined in modeling high-frequency financial price series and other irregularly spaced discrete data. GJR. AGARCH1 (Asymmetric GARCH) The AGARCH model was introduced by Engle (1990) to allow for asymmetric effects of negative and positive innovations (see also EGARCH.1) model of Nam. ANN-ARCH (Artificial Neural Network ARCH) Donaldson and Kamstra (1997) term the GJR model (see GJR) augmented with a logistic function. ANST-GARCH (Asymmetric Nonlinear Smooth Transition GARCH) The ANST-GARCH(1. for which surely. in which the conditional transition probabilities between the different values are guaranteed to lie between zero and one and sum to unity. and VGARCH1). where negative values of γ implies that positive shocks will result in smaller increases in future volatility than negative shocks of the same absolute magnitude. Many other more complicated Stable GARCH formulations have subsequently been proposed and analyzed in the literature (see SGARCH). The AGARCH(1. Engle and Sheppard (2006) extends the DCC model (see DCC) to allow for asymmetries in the time-varying conditional correlations based on a GJR threshold type formulation (see GJR). and readily ensures that the conditional variance is positive almost AGARCH2 (Absolute value GARCH) See TS-GARCH. the ANN-ARCH model.1) model is defined by: . The model may alternative be expressed as: . ADCC (Asymmetric Dynamic Conditional Correlations) The ADCC GARCH model of Cappiello. ACM (Autoregressive Conditional Multinomial) The ACM model of Engle and Russell (2005) involves an ARMA type representation for discrete-valued multinomial data. Pyun and Arize (2002) postulates that -2- .. as commonly used in Neural Networks. NAGARCH.

inflationary uncertainty. . The model simplifies to the ST-GARCH(1.q) model for and .q) model for . in which the skewness is allowed to be time-varying. . In particular. where ..1) model of Gonzalez-Rivera (1998) for (see ST-GARCH) and the standard GARCH(1. Most empirical applications of the ARCD model have relied on the standardized skewed Student-t distribution (see also GARCH-t and GED-GARCH). for the GARCHS(1. reduces to the standard linear GARCH(p. explicitly parameterizing the shape parameters of this distribution as a function of lagged information.K. the TGARCH(p. the ARCH class of models has subsequently found especially wide use in characterizing time-varying financial -3- . In particular. the GARCH with Skewness and Kurtosis.q) model is obtained as the limiting case of the model for and (see GARCH. parameterizes the conditional kurtosis as: . TSGARCH. model of León. or GARCHS. APARCH (Asymmetric Power ARCH) The APARCH. the TS-GARCH(p. model of Harvey and Siddique (1999). ARCH (AutoRegressive Conditional Heteroskedastcity) The ARCH model was originally developed by Engle (1982) to describe U.q) model. or APGARCH. while the log-GARCH(p. GJR.q) model for and . However. the NGARCH(p.1) model for (see GARCH). Granger and Engle (1993) nests several of the most popular univariate parameterizations. where denotes a smooth transition function.1) model. model of Ding.1. or GARCHSK. the GJR-GARCH model for and . Rubio and Serna (2005). NGARCH. Specific examples of ARCD models include the GARCH with Skewness. ARCD (AutoRegressive Conditional Density) The ARCD class of models proposed by Hansen (1994) extends the basic ARCH class of models to allow for conditional dependencies beyond the mean and variance by postulating a specific non-normal distribution for the standardized innovations . TGARCH and log-GARCH). where .q) model for and . Similarly. the APGARCH(p.

More generally. The qth-order linear ARCH(q) model suggested by Engle (1982) provides a particularly convenient and natural parameterizarion for capturing the tendency for large (small) variances to be followed by other large (small) variances. where is a sequence of independent random variables with mean zero and unit variance. . were based on the linear ARCH(q) model with the additional constraint that the αi’s decline linearly with the lag. -4- . Even though analytical expressions for the Maximum Likelihood Estimates (see also QMLE) are not available in closed form. the log-likelihood function for the ARCH model may be expressed as: . and the conditional variance. The ARCH regression model for by: . . ARCH-Filters ARCH and GARCH models may alternatively be given a non-parametric interpretation as discrete-time filters designed to extract information about some underlying. . where first analyzed in Engle (1982) is defined refers to the information set available at time t-1. is an explicit function of the p lagged innovations. . in turn requiring the estimation of only a single α parameter irrespective of the value of q. where for the conditional variance to non-negative and the model well-defined ω has to be positive and all of the αi’s non-negative. any non-trivial measurable function of the time t-1 information volatility. Most of the early empirical applications of ARCH models. including Engle (1982). Using a standard prediction error decomposition type argument. numerical procedures may easily be used to maximize the function. . is now commonly referred to as an ARCH model. such that .

extend the ARCH and GARCH models and corresponding ARCH-Filters based solely on past observations (see ARCH-Filters) to allow for the use of both current and future observations in the estimation of the latent volatility. The model is designed to capture slowly decaying stochastic long-run volatility dependencies (see also CGARCH1.S. IGARCH). interest rates. For instance. . ARCH-NNH (ARCH Nonstationary Nonlinear Heteroskedasticity) The ARCH-NNH model of Han and Park (2008) includes a nonlinear function of a near or exact unit root process. . stochastic volatility process. -5- . ARCH-Smoothers ARCH-Smoothers. in the conditional variance of the ARCH(1) model. xt . first developed by Nelson (1996b) and Foster and Nelson (1996). so that the two sets of parameters must be estimated jointly to achieve asymptotic efficiency. Multivariate extensions of the ARCH-M model were first analyzed and estimated by Bollerslev. Non-linear functions of the conditional variance may be included in the conditional mean in a similar fashion. Lilien and Robins (1987) parameterizes the conditional mean as a function of . ARCH-SM (ARCH Stochastic Mean) The ARCH-SM acronym was coined by Lee and Taniguchi (2005) to distinguish ARCH models in which (see ARCH). FIGARCH. ARCH-M (ARCH-in-Mean) The ARCH-M model was first introduced by Engle. the asymptotically efficient filter (in a mean-square-error sense for increasingly finer sample observations) for the instantaneous volatility in the GARCH diffusion model (see GARCH Diffusion) is given by the discrete-time GARCH(1. Engle and Wooldridge (1988) (see also MGARCH1).1) model (see also ARCH-Smoothers). Lilien and Robins (1987) for modelling risk-return tradeoffs in the term structure of U. Issues related to the design of consistent and asymptotically optimal ARCH-Filters have been studied extensively by Nelson (1992. 1996a) and Nelson and Foster (1994). The model extends the ARCH regression model in Engle (1982) (see ARCH) by allowing the conditional mean to depend directly on the conditional variance. This breaks the block-diagonality between the parameters in the conditional mean and the parameters in the conditional variance. The final preferred model estimated in Engle.possibly latent continuous-time.

BEKK (Baba. GJR.1) model may be expressed as: .1) model of Crouhy and Rockinger (1997) combines and extends the TS-GARCH(1. Kraft and Kroner) The BEKK acronym refers to a specific parameteriztion -6- . the Threshold GARCH model. including the standard linear GARCH model. β-ARCH (Beta ARCH) The β-ARCH(1) model of Guégan and Diebolt (1994) allows the conditional variance to depend asymmetrically on positive and negative lagged innovations. and VGARCH1). NGARCH. EGARCH. and denotes the corresponding standardized innovations. . the GJR-GARCH model. the Nonlinear GARCH model. Higher order ATGARCH(p. the Exponential GARCH model. The Aug-GARCH(1. . More general β-ARCH(q) and β-GARCH(p. AVGARCH (Absolute Value GARCH) See TS-GARCH.q) models may be defined in a similar fashion (see also GJR. where I( @ ) denotes the indicator function.ATGARCH (Asymmetric Threshold GARCH) The ATGARCH(1. For and the model reduces to the standard linear ARCH(1) model. the Multiplicative GARCH model.1) model is obtained by fixing and . TGARCH. TS-GARCH and VGARCH1). where . and the VGARCH model (see GARCH. Aug-GARCH (Augmented GARCH) The Aug-GARCH model developed by Duan (1997) nests most of the popular univariate parameterizations. MGARCH2. while the EGARCH model corresponds to and (see also HGARCH).1) and GJR(1.1) models (see TSGARCH and GJR) by allowing the threshold used in characterizing the asymmetric response to differ from zero. The basic GARCH(1. TGARCH. the Taylor-Schwert GARCH model.q) models may be defined analogously (see also AGARCH and TGARCH). Engle.

Alternative models allowing for asymmetries may be specified in a similar manner. This formulation would be correctly specified if the underlying process for follows a GARCH(1.d. Baba and D.q) model proposed by Chou (2005) postulates a GARCH(p. where denotes the N×N matrix of conditional correlations with typical element . say . BGARCH (Bivariate GARCH) See MGARCH1. The reference to Y. -7- . This quadratic representation automatically guarantees that t is positive definite. CAViaR (Conditional Autoregressive Value at Risk) The CAViaR model of Engle and Manganelli (2004) specifies the evolution of a particular conditional quantile of a times series. as an autoregressive process. may always be decomposed as: . The model is essentially analogous to the ACD model (see ACD) for the times between randomly occurring events (see also REGARCH). standardized innovations (see GARCH). CCC (Constant Conditional Correlations) The N×N conditional covariance matrix for the N×1 vector process . say where for some pre-specified fixed level p. The CAViaR model was explicitly developed for predicting quantiles in financial asset return distributions. The simplest BEKK representation for the N×N conditional covariance matrix t takes the form: . The indirect GARCH(1.1) model with i.i. and A and B are both unrestricted N×N matrices.q) structure (see GARCH) for the dynamic dependencies in time series of high-low asset prices over some fixed time interval. Kraft in the acronym stems from an earlier unpublished fourauthored working paper. or so-called Value-at-Risk.of the multivariate GARCH model (see MGARCH1) developed in Engle and Kroner (1995). CARR (Conditional AutoRegressive Range) The CARR(p.1) model parameterizes the conditional quantiles as: . where C denotes an upper triangular N×N matrix.

so that the temporal variation in is determined solely by the time-varying conditional variances for each of the elements in . . requiring only the non-linear estimation of N univariate GARCH models. -8- . This assumption greatly simplifies the inference. . the CGARCH model may alternatively be expressed as a restricted GARCH(2. as long as each of the conditional variances are positive. The CCC GARCH model of Bollerslev (1990) assumes that the conditional correlations are constant . where refers to the unconditional variance.1) model proposed by Klüppelberg. CGARCH1 (Component GARCH) The component GARCH model of Engle and Lee (1999) was designed to better account for long-run volatility dependencies. with the corresponding long-run variance parameterized by the separate equation.1) model as: . Moreover. the CGARCH model is obtained by relaxing the assumption of a constant . Specifically. COGARCH (Continuous GARCH) The continuous-time COGARCH(1. while may be estimated by the sample correlations of the corresponding standardized residuals. and . Censored-GARCH See Tobit-GARCH. Lindner and Maller (2004) may be expressed as. the CCC model guarantees that the resulting conditional covariance matrices are positive definite (see also DCC and MGARCH1). Substituting this expression for into the former equation. CGARCH2 (Composite GARCH) The CGARCH model of den Hertog (1994) represents as the sum of a latent permanent random walk component and another latent AR(1) component. . Rewriting the GARCH(1.2) model (see also FIGARCH).and denotes the N×N diagonal matrix with typical element .

the COGARCH model is driven by a single innovation process. DAGARCH (Dynamic Asymmetric GARCH) The DAGARCH model of Caporin and McAleer (2006) extends the GJR-GARCH model (see GJR) to allow for multiple thresholds and timevarying asymmetric effects (see also AGARCH.where . e. In contrast to the GARCH diffusion model of Nelson (1990b) (see GARCH Diffusion).1) model (see GARCH).g. . ATGARCH and TGARCH). Higher order COGARC(p. where . see. To facilitate the analysis of large dimensional systems. A closely related formulation was proposed -9- . Jondeau and Rockinger (2006) and Patton (2006) (see also CCC and DCC). DCC (Dynamic Conditional Correlations) The multivariate DCC-GARCH model of Engle (2002a) extends the CCC model (see CCC) by allowing the conditional correlations to be timevarying.. DCC and MGARCH1). CorrARCH (Correlated ARCH) The bivariate CorrARCH model of Christodoulakis and Satchell (2002) parameterizes the time-varying conditional correlations as a distributed lag of the product of the standardized innovations from univariate GARCH models for each of the two series. A Fisher transform is used to ensure that the resulting correlations always lie between -1 and 1 (see also CCC. and denotes the N×1 vector innovation process. The class of copula GARCH models builds on this idea in the formulation of multivariate GARCH models (see MGARCH1) by linking univariate GARCH models through a sequence of possibly time-varying conditional copulas. For further discussion of estimation and inference in copula GARCH models. The model is obtained by backward solution of the difference equation defining the discrete-time GARCH(1. replacing the standardized innovations by the increments to the Lévy process.q) processes have been developed by Brockwell. which involves two independent Brownian motions. Chadraa and Lindner (2006) (see also ECOGARCH). Copula GARCH Any joint distribution function may be expressed in terms of its marginal distribution functions and a copula function linking these. the basic DCC model postulates that the temporal variation in the conditional correlations may be described by exponential smoothing (see EWMA) so that .

. or so-called leverage effects. 1991) that if each of the three N×N matrices and are positive definite. In particular. or matrix element-by-element multiplication. CorrARCH. or VCC-MGARCH model (see also ADCC. who refer to their approach as a Varying Conditional Correlation. say .independently by Tse and Tsui (2002). DTARCH (Double Threshold ARCH) The DTARCH model of Li and Li (1996) allows the parameters in both the conditional mean and the conditional variance to change across regimes. FDCC and MGARCH1). EGARCH (Exponential GARCH) The EGARCH model was developed by Nelson (1991). diag MGARCH (diagonal GARCH) The diag MGARCH model refers to the simplification of the vech GARCH model (see vech GARCH) in which each of the elements in the conditional covariance matrix depends on its own past values and the products of the corresponding elements in the innovation vector only. The model explicitly allows for asymmetries in the relationship between return and volatility (see also GJR and TGARCH). which is typically observed empirically with equity index returns. the conditional covariance matrix will also be positive definite (see also MGARCH1). The model is conveniently expressed in terms of Hadamard products. The model may be seen as a continuous-time analog of the discrete-time EGARCH model (see also EGARCH. This effect. It follows (see Attanasio. for the diag MGARCH(1. DVEC-GARCH (Diagonal VECtorized GARCH) See diag MGARCH.1) model may then be expressed as: . with the m different regimes determined by a set of threshold parameters for some lag k$1 of the observed process. Lindner and Maller (2004) (see COGARCH) to allow for different impact of positive and negative jump innovations. For negative shocks will obviously have a bigger impact on future volatility than positive shocks of the same magnitude. is often referred to as a “leverage effect. ECOGARCH (Exponential Continuous GARCH) The continuous-time ECOGARCH model developed by Haug and Czado (2007) extends the Lévy driven COGARCH model of Klüppelberg.” although it is now widely agreed that the -10- . The EGARCH(1. In particular. GJR and TGARCH). let denote the standardized innovations.1) model. where (see also TGARCH).

advocating the use of with daily financial returns. EVT-GARCH (Extreme Value Theory GARCH) The EVT-GARCH approach pioneered by McNeil and Frey (2000). This is especially useful when conditioning on other explanatory variables. or Value-at-Risk. respectively. More specifically.apparent asymmetry has little to do with actual financial leverage. and α and β are both scalar parameters (see also OGARCH and MGARCH1). Meanwhile. random variables and corresponding generalized Pareto distributions for more accurately characterizing the tails of the distributions of the standardized innovations from GARCH models. -11- . GARCH-t and GED-GARCH). . Ng and Rothschild (1990) assumes that the temporal variation in the N×N conditional covariance matrix for a set of N returns can be described by univariate GARCH models for smaller set of K<N portfolios.i. The EWMA approach to variance estimation was popularized by RiskMetrics. EWMA covariance measures are readily defined in a similar manner. model in which .d. EWMA (Exponentially Weighted Moving Average) EWMA variance measures are defined by the recursion. the EGARCH model also avoids complications from having to ensure that the process remains positive. EWMA may be seen as a special case of the GARCH(1.1) model may be expressed as: where w denotes an N×1 vector. and (see GARCH and IGARCH). or IGARCH(1.1). type predictions (see also CAViaR. By parameterizing the logarithm of the conditional variance as opposed to the conditional variance.1). the logarithmic transformation complicates the construction of unbiased forecasts for the level of future variances (see also GARCH and log-GARCH). relies on extreme value theory for i. where and refer to the time invariant N×1 vector of factor loadings and time t conditional th variance for the k factor. F-ARCH (Factor ARCH) The multivariate factor ARCH model developed by Diebold and Nerlove (1989) (see also Latent GARCH) and the factor GARCH model of Engle. . This idea may be used in the calculation of low-probability quantile. the F-GARCH(1.

q) and the APARCH(p. including the DTARCH. the FIEGARCH(1. In particular. For 0<d<1 this representation implies fractional integrated slowly decaying hyperbolic dependencies in (see also FIGARCH. FIAPARCH (Fractionally Integrated Power ARCH) The FIAPARCH(p. STGARCH. and the roots of and are all outside the unit circle.1) model may be conveniently expressed as: . HYGARCH and LMGARCH).d. For values of 0<d<½ the model implies an eventual slow hyperbolic decay in the autocorrelations for (see also FIEGARCH. FIEGARCH (Fractionally Integrated EGARCH) The FIEGARCH model of Bollerslev and Mikkelsen (1996) imposes a fractional unit root in the autoregressive polynomial in the ARMA representation of the EGARCH model (see EGARCH). allowing for fractional orders of integration in the autoregressive polynomial in the corresponding ARMA representation. FIREGARCH (Fractionally Integrated Range EGARCH) See REGARCH. FIGARCH (Fractionally Integrated GARCH) The FIGARCH model proposed by Baillie. 0<d<1. The model may be seen as natural extension of the IGARCH model (see IGARCH). with the weights assigned to each model determined by a set of logistic functions.d.d.q) models in parameterizing as a fractionally integrated distributed lag of (see FIGARCH and APARCH).FCGARCH (Flexible Coefficient GARCH) The FCGARCH model of Medeiros and Veiga (2008) defines the conditional variance as a linear combination of standard GARCH type models. Caporin and Gobbo (2006) generalizes the basic DCC model (see DCC) to allow for different dynamic dependencies in the time-varying conditional correlations (see also ADCC). where . . GJR.q) model of Tse (1998) combines the FIGARCH(p. TGARCH. FDCC (Flexible Dynamic Conditional Correlations) The FDCC-GARCH model of Billio. The model nests several alternative smooth transition and asymmetric GARCH models as special limiting cases. and VSGARCH models. Bollerslev and Mikkelsen (1996) relies on an ARFIMA type representation to better capture the long-run dynamic dependencies in the conditional variance. HYGARCH and LMGARCH). FGARCH (Factor GARCH) See F-ARCH. -12- .

The GARCH(1. and then subsequently “paste” together the parameter estimates subject to the constraint that the resulting parameter matrices for the full N-dimensional MGARCH model guarantee positive semidefinite conditional covariance matrices. This is accomplished by estimating a set bivariate MGARCH models for each of the N(N+1)/2 possible different pairwise combinations of the N variables.1) model is well-defined and the conditional variance positive almost surely provided that and . This particular parameterization was also proposed independently by Taylor (1986). Conditions on the parameters to ensure that the GARCH(p. where h$2 denotes the horizon of the forecast. . The relatively simple GARCH(1.q) model may alternative be represented as an ARMA(max{p. . The GARCH(1. -13. often provides a good fit in empirical applications.q) conditional variance is always positive are given in Nelson and Cao (1992).Flex-GARCH (Flexible GARCH) The multivariate Flex-GARCH model of Ledoit.1) model may readily be calculated as: .1) model may alternatively be express as an ARCH(4) model. where . GARCH (Generalized AutoRegressive Conditional Heteroskedasticity) The GARCH(p. The GARCH(p. . provided that .q) model of Bollerslev (1986) includes p lags of the conditional variance in the linear ARCH(q) (see ARCH) conditional variance equation. GAARCH (Generalized Augmented ARCH) See AARCH. so that by definition . Santa-Clara and Wolf (2003) is designed to reduce the computational burden involved in the estimation of multivariate diagonal MGARCH models (see diag MGARCH). If the model is covariance stationary and the unconditional variance equals . Multi-period conditional variance forecasts from the GARCH(1.p) model for the squared innovation: .q}.1) model.

and . GARCH-Γ refers to the gamma obtained under the assumption that the return on the underlying asset follows a GARCH process. where . converges weakly to a GARCH diffusion model for COGARCH and ARCH-Filters). tend to be fairly close to their Black-Scholes counterparts. that drive the observable process and the instantaneous latent volatility process. are assumed to be independent.1) models defined over discrete time intervals of length . GARCH Diffusion The continuous-time GARCH diffusion model is defined by: . GARCH-M (GARCH in Mean) See ARCH-M. .GARCH-∆ (GARCH Delta) See GARCH-Γ. GARCH-∆’s. Options gamma play an important role in hedging volatility risk embedded in options positions. -14- . where the two Wiener processes. GARCH-Γ (GARCH Gamma) The gamma of an option is defined as the second derivative of the option price with respect to the price of the underlying asset. Meanwhile. Engle and Rosenberg (1995) find that GARCH-Γ’s are typically much higher than conventional Black-Scholes gammas. For the model reduces to a standard AR(1) model. the sequence of GARCH(1. As shown by Nelson (1990b). or the first derivative of the option price with respect to the price of the underlying asset. but for and the magnitude of the serial correlation in the mean will be a decreasing function of the conditional variance (see also ARCH-M). and . . . (see also GARCH-EAR (GARCH Exponential AutoRegression) The GARCH-EAR model of LeBaron (1992) allows the first order serial correlation of the underlying process to depend directly on the conditional variance.

GARJI Maheu and McCurdy (2004) refer to the standard GARCH model (see GARCH) augmented with occasional Poisson distributed “jumps” or large moves. . GARCHSK (GARCH with Skewness and Kurtosis) See ARCD. Combining -15- . where denotes the degrees of freedom to be estimated along with the parameters in the conditional variance equation (see also GED-GARCH. say . as an explanatory variable in the conditional covariance matrix (see also 1 MGARCH ) GARCH-X2 The GARCH-X model proposed by Brenner. where the time-varying jump intensity is determined by a separate autoregressive process as a GARJI model. However.GARCHS (GARCH with Skewness) See ARCD. GARCH-X1 The multivariate GARCH-X model of Lee (1994) includes the error correction term from a cointegrating type relationship for the underlying vector process . Engle and Sheppard (2006) utilizes a more flexible BEKK type parameterization (see BEKK) for the dynamic conditional correlations (see DCC). appear to have fatter tails than the normal distribution. GARCHX The GARCHX model proposed by Hwang and Satchell (2005) for modeling aggregate stock market return volatility includes a measure of the lagged cross-sectional return variation as an explanatory variable in the GARCH conditional variance equation (see GARCH). Harjes and Kroner (1996) for modeling short term interest rates includes the lagged interest rate raised to some power. as an explanatory variable in the GARCH conditional variance equation (see GARCH). GARCH-t (GARCH t-distribution) ARCH models are typically estimated by maximum likelihood under the assumption that the errors are conditionally normally distributed (see ARCH). in many empirical applications the standardized residuals. say . The GARCH-t model of Bollerslev (1987) relaxes the assumption of conditional normality by instead assuming that the standardized innovations follow a standardized Student t-distribution. The corresponding log Likelihood function may be expressed as: . GDCC (Generalized Dynamic Conditional Correlations) The multivariate GDCC-GARCH model of Cappiello. QMLE and SPARCH).

model of Engle (1990) (see AGARCH). GO-GARCH and MGARCH1). GJR (Glosten. This asymmetry is sometimes referred to in the literature as a “leverage effect. or what is also sometimes referred to as an exponential power distribution (see also GARCH-t). This formulation permits estimation by a relatively easy-toimplement two-step procedure (see also F-ARCH. or AGARCH. or TGARCH. so that the volatility increases proportionally more following negative than positive shocks. the model may alternatively be -16- .q) model of Sentana (1995) is defined by: . The GJR formulation is closely related to the Threshold GARCH. model proposed independently by Zakoian (1994) (see TGARCH).1) model may be expressed as: .” although it is now widely agreed that it has little to do with actual financial leverage (see also EGARCH). and is diagonal with the conditional variances for each of the components along the diagonal. γ is typically found to be positive. The model simplifies to the linear GARCH(p.q) model if all of the ’s and the ’s are equal to zero. model of Glosten. Jagannathan and Runkle (1993) allows the conditional variance to respond differently to the past negative and positive innovations. GQARCH (Generalized Quadratic ARCH) The GQARCH(p. GO-GARCH (Generalized Orthogonal GARCH) The multivariate GO-GARCH model of van der Weide (2002) assumes that the temporal variation in the N×N conditional covariance matrix may be expressed in terms of N conditionally uncorrelated components. where I( @ ) denotes the indicator function. or just GJR. where denotes a N×N matrix. Defining the q×1 vector . Jagannathan and Runkle GARCH) The GJR-GARCH.the ADCC (see ADCC) and the GDCC models results in an AGDCC model (see also FDCC). The model is also sometimes referred to as a SignGARCH model. The GJR(1. GED-GARCH (Generalized Error Distribution GARCH) The GED-GARCH model of Nelson (1991) replaces the assumption of conditionally normal errors traditional used in the estimation of ARCH models with the assumption that the standardized innovations follow a generalized error distribution. and the Asymmetric GARCH. . When estimating the GJR model with equity index returns.

The model is motivated as arising from the interaction of traders with different investment horizons. the model is formulated in such a way that it breaks the path-dependence which complicates the estimation of the SWARCH model of Cai (1994) and Hamilton and Susmel (1994) (see SWARCH). HYGARCH (Hyperbolic GARCH) The HYGARCH model proposed by Davidson (2004) nests -17- . Puctet and Weizsäcker (1997) parameterizes the conditional variance as a function of the square of the sum of lagged innovations. AGARCH1. Davé. The HARCH model may been interpreted as a restricted QARCH model (see GQARCH). EGARCH. The model obviously reduces to the standard linear GARCH(1. The HGARCH(1. Conditions on the parameters for the conditional variance to be positive almost surely and the model well-defined are given in Sentana (1995) (see also AARCH). TGARCH. GJR. Heston GARCH See SQR-GARCH. over different horizons. Dacorogna. GQTARCH (Generalized Qualitative Threshold ARCH) See QTARCH. GRS-GARCH (Generalized Regime-Switching GARCH) The RGS-GARCH model proposed by Gray (1996) allows the parameters in the GARCH model to depend upon an unobservable latent state variable governed by a first-order Markov process. NGARCH. HGARCH (Hentschel GARCH) The HGARCH model of Hentschel (1995) is based on a BoxCox transform of the conditional standard deviation. or the squared lagged returns.1) model for and . . By aggregating the conditional variances over all of the possible states at each point in time. Olsen.1) model may be expressed as: .expressed as: . and TS-GARCH models as special cases (see also Aug-GARCH). where Ψ denotes the q×1 vector of coefficients and A refer to the q×q symmetric matrix of and coefficients. It is explicitly designed to nest some of the most popular univariate parameterizations. HARCH (Heterogeneous ARCH) The HARCH(n) model of Müller. but it also nests the APARCH.

it is still strictly stationary with a well defined non-degenerate limiting distribution.q}. typically Black-Scholes. IGARCH and FIGARCH). A leading example is the N-dimensional factor ARCH model of Diebold and Nerlove (1989). where . The standard GARCH and FIGARCH models correspond to .q) model as an ARMA(max{p. is sometimes referred to as an LARCH model. For the HYGARCH model reduces to a standard GARCH or an IGARCH model depending upon whether or . or (see also FIGARCH). respectively. Even though the IGARCH model is not covariance stationary.p) model for the squared innovations. This representation was first used by Robinson (1991) in the derivation of general tests for conditional heteroskedasticity. standard inference procedures may be applied in testing the hypothesis of a unit root. LARCH (Linear ARCH) The ARCH(4) representation. so that the model may be written as: . IGARCH and FIGARCH models (see GARCH.q) model (see GARCH) often results in the sum of the estimated and coefficients being close to unity. as shown by Lee and Hansen (1994) and Lumsdaine (1996). and and .the GARCH. and and denote appropriately defined lag polynomials. Rewriting the GARCH(p. models. Also. IV (Implied Volatility) Implied volatility refer to the volatility that would equate the theoretical price of an option according to some valuation model. . or unobserved GARCH. IGARCH (Integrated GARCH) Estimates of the standard linear GARCH(p. see Nelson (1990a). Latent GARCH Models formulated in terms of latent variables that adhere to GARCH structures are sometimes referred to as latent GARCH. to that of the actual market price of the option. . -18- . the IGARCH model of Engle and Bollerslev (1986) imposes an exact unit root in the corresponding autoregressive polynomial. The model is defined in terms of the ARCH(4) representation (see also LARCH). .

where follows a GARCH(1.q) model (see GARCH) in which the conditional variance is a linear function of p own lags and q lagged squared innovations is sometimes refereed to as an LGARCH model. for which the likelihood functions are readily available through a prediction error decomposition type argument (see ARCH). LMGARCH (Long Memory GARCH) The LMGARCH(p. Provided that the fourth order moment exists. the likelihood functions for latent GARCH models are generally not available in closed form. where . LGARCH1 (Leverage GARCH) The GJR model is sometimes referred to as an LGARCH model (see GJR). log-GARCH (Logarithmic GARCH) The log-GARCH(p. The Level-GARCH model is also sometimes referred to as Time-Varying Parameter Level. model (see also GARCH and GARCH-X2).5. the resulting process for is covariance stationary and exhibits long memory. Sentana and Shephard (2004) (see also SV). innovations respectively. General estimation and inference procedures for latent GARCH models based on Markov Chain Monte Carlo methods have been developed by Fiorentini. and the conditional variance of is determined by an ARCH model in lagged squared values of the latent factor (see also F-ARCH).1) model.1) structure. For further discussion comparisons with the FIGARCH model see Conrad and Karanasos (2006) (see also FIGARCH and HYGARCH). and 0<d<0. Models in which the innovations are subject to censoring is another example (see Tobit-GARCH). .d. or TVP-Level. Harjes and Kroner (1996) for modeling the conditional variance of short term interest rates postulates that .d.q) model is defined by. For the model obviously reduces to a standard GARCH(1.i. LGARCH2 (Linear GARCH) The standard GARCH(p.. . Level-GARCH The Level-GARCH model proposed by Brenner.q) model. In contrast to standard ARCH and GARCH models. which was suggested -19- . where and denote N×1 vectors of factor loadings and i.

independently in slightly different forms by Geweke (1986). MARCH2 (Multiplicative ARCH) See MGARCH2. MAR-ARCH (Mixture AutoRegressive ARCH) See MGARCH3. The model may alternatively be expressed as: . or E-MACH(p). . the Linear MACH(1). or Q-MACH(p). In light of this alternative representation. . Pantula (1986) and Milhøj (1987). MARCH1 (Modified ARCH) Friedman. The standard linear ARCH(1) model. Exponential MACH(p). Laibson and Minsky (1989) denote the class of GARCH(1. In their estimation of the model Friedman. the model is also sometimes referred to as a Multiplicative GARCH. model. or L-MACH(1). models. models. Higher order L-MACH(p) models.1) models in which the conditional variance depends non-linearly on the lagged squared innovations as Modified ARCH models. Matrix EGARCH The multivariate matrix exponential GARCH model of Kawakatsu (2006) (see also EGARCH and MGARCH1) specifies the second moment dynamics in terms of the -20- . where F( @ ) denotes a positive valued function. may be defined in a similar manner (see also EGARCH and GQARCH). . Quadratic MACH(p). Laibson and Minsky (1989) use the function (see also NGARCH). More specifically. is not a MACH(1) process. parameterizes the logarithmic conditional variance as a function of the lagged logarithmic variances and the lagged logarithmic squared innovations. so that the effect of a shock to the conditional variance lasts for at most p periods. model is defined by . MACH (Moving Average Conditional Heteroskedastic) The MACH(p) class of models proposed by Yang and Bewley (1995) is formally by the condition: . or MGARCH.

and is a nonnegative i. . the cumulative trading volume or the number of quotes. let denote the N(N+1)/2×1 vector of unique elements in . The conditional mean is natural parameterized as. and specific formulations are readily estimated by the corresponding software for GARCH models.1) model may then be expressed as: . represent the accumulated effect of numerous within period.matrix logarithm of the conditional covariance matrix. MDH (Mixture of Distributions Hypothesis) The MDH first developed by Clark (1973) postulates that financial returns over non-trivial time intervals. The MEM may be expressed as. refers to its conditional mean.q) model (see GARCH). for appropriately dimensioned matrices and . MGARCH1 (Multivariate GARCH) Multivariate GARCH models were first analyzed and -21- . where conditions on the parameters for to be positive follows from the corresponding conditions for the GARCH(p. MEM (Multiplicative Error Model) The Multiplicative Error class of Models (MEM) was proposed by Engle (2002b) as a general framework for modeling non-negative valued time series. . the MEM class of models encompasses all ARCH and GARCH models. where denotes the time series of interest. in asset returns. The MDH coupled with the assumption of serially correlated news arrivals is often used to rationalize the apparent volatility clustering. have been developed and explored empirically by Tauchen and Pitts (1983) and Andersen (1996) among many others. or intraday. A simple multivariate matrix EGARCH extension of the univariate EGARCH(1. The ACD model for durations may also be interpreted as a MEM (see ACD). say one day.d. such as the number of trades. By parameterizing only the unique elements of the logarithmic conditional covariance matrix. or ARCH effects. Defining and .i. More specifically. news arrivals and corresponding price changes. More advanced versions of the MDH. the matrix EGARCH model automatically guarantees that is positive definite. relating the time-deformation to various financial market activity variables. process with unit mean. where the logarithm of a matrix is defined by the inverse of the power series expansion used in defining the matrix exponential.

This diagonal simplification.1) model of Engle and Ng (1993) is defined by: . Engle and Wooldridge (1988) assumes that the and matrices are both diagonal. Also. representations. The trivariate vech MGARCH(1. -22- . NAGARCH (Nonlinear Asymmetric GARCH) The NAGARCH(1. or N=2. MGARCH and VGARCH acronyms are used interchangeably (see MGARCH1). Pantula (1986) and Milhøj (1987). the 4 3 2 model involves a total of N(N+1)/2 + (p+q)(N + 2N +N )/4 parameters. Engle and Wooldridge (1988).estimated empirically by Bollerslev. The model is more commonly refereed to as the log-GARCH model (see log-GARCH). and the and matrices are all of compatible dimension N(N+1)/2×N(N+1)/2. The unrestricted linear MGARCH(p. NMGARCH and SWARCH). resulting in “only” (1+p+q)(N2 + N)/2 parameters to be estimated. Li and Yuen (2006) postulates that the time t conditional variance is given by a time-invariant mixture of different GARCH models (see also GRS-GARCH. MV-GARCH (MultiVariate GARCH) The MV-GARCH.q) model is defined by: . so that each element in depends exclusively on its own lagged value and the product of the corresponding shocks. is often denoted as a diag MGARCH model (see also diag MGARCH). MS-GARCH (Markov Switching GARCH) See SWARCH.1) model estimated in Bollerslev. yet empirically realistic. MGARCH3 (Mixture GARCH) The MAR-ARCH model of Wong and Li (2001) and the MGARCH model Zhang. where vech( @ ) denotes the operator that stacks the lower triangular portion of a symmetric N×N matrix into an N(N+1)/2×1 vector of the corresponding unique elements. The general vech representation does not guarantee that the resulting conditional covariance matrices are positive definite. that easily ensure the conditional covariance matrices are positive definite. which becomes prohibitively expensive from a practical computational point of view for anything but the bivariate case. This vectorized representation is also sometime referred to as a VECH GARCH model. MGARCH2 (Multiplicative GARCH) Slightly different versions of the univariate Multiplicative GARCH model was proposed independently by Geweke (1986). Much of the research on multivariate GARCH models has been concerned with the development of alternative more parsimonious.

Consequently. although not always significantly so (see also APARCH and TS-GARCH). the conditional covariance matrix for may be expressed as: . OGARCH (Orthogonal GARCH) The multivariate OGARCH model assumes that the N×1 vector process may be represented as .1) model have been studied extensively by Alexander and Lazar (2006) (see also GARCH-t. . The OGARCH model is also sometimes referred to as a principal component -23- . where the columns of the N×m matrix are mutually orthogonal. With most financial rates of returns.q) model proposed by Higgins and Bera (1992) parameterizes the conditional standard deviation raised to the power δ as a function of the lagged conditional standard deviations and the lagged absolute innovations raised to the same power. NL-GARCH (Non-Linear GARCH) The NL-GARCH acronym is sometimes used to describe all parameterizations different from the benchmark linear GARCH(p. 2008).Higher order NAGARCH(p.q) models may be defined similarly (see also AGARCH1 and VGARCH1).q) model for δ=2 (see GARCH). where denotes the m×m diagonal matrix with the conditional factor variances along the diagonal. the estimates for δ are found to be less than two. GED-GARCH and SWARCH). NGARCH (Nonlinear GARCH) The NGARCH(p.q) representation (see GARCH). A slightly different version of the NGARCH model was originally estimated by Engle and Bollerslev (1986). The NGARCH model is also sometimes referred to as a Power ARCH or Power GARCH model. NM-GARCH (Normal Mixture GARCH) The NM-GARCH model postulates that the distribution of the standardized innovations is determined by a mixture of two or more normal distributions. The statistical properties of the NM-GARCH(1. . or PARCH or PGARCH model. This formulation obviously reduces to the standard GARCH(p. and the m elements in the m×1 vector process are conditionally uncorrelated with GARCH conditional variances. Estimation and inference in the OGARCH model are discussed in detail in Alexander (2001.

reflecting how the conditional variance responds to different sized shocks (see also GJR and TGARCH). and denote the QMLE (Quasi Maximum Likelihood Estimation) ARCH models are typically estimated under the assumption of conditional normality (see ARCH). QARCH (Quadratic ARCH) See GQARCH. . the PGARCH(1. where refers to the stage of the periodic cycle at time t. and m is an integer. MGARCH1 and PC-GARCH). where σ denotes the unconditional standard deviation of the process. In particular.1) model is defined by: . GO-GARCH. GED-GARCH and SPARCH). PARCH (Power ARCH) See NGARCH.1) parameter values for . PC-GARCH (Principal Component GARCH) The multivariate PC-GARCH model of Burns (2005) is based on the estimation of univariate GARCH models to the principal components defined by the covariance matrix for the standardized residuals from a first stage estimation of univariate GARCH models for each of the individual series (see also OGARCH). PGARCH2 (Power GARCH) See NGARCH. PGARCH1 (Periodic GARCH) The PGARCH model of Bollerslev and Ghysels (1996) was designed to account for periodic dependencies in the conditional variance by allowing the parameters of the model to vary over the cycle. The approach is related to but formally different from the PC-GARCH model of Burns (2005) (see also F-ARCH. the parameter estimates -24- . . The PNP-ARCH model was used by Engle and Ng (1993) in the construction of so-called news impact curves. and different GARCH(1. PNP-ARCH (Partially Non-Parametric ARCH) The PNP-ARCH model estimated by Engle and Ng (1993) allows the conditional variance to be a partially linear function of the lagged innovations and the lagged conditional variance.MGARCH model. Even if the assumption of conditional normality is violated (see also GARCH-t.

or GQTARCH(p. RGARCH2 (Robust GARCH) The robust GARCH model of Park (2002) is designed to minimize the impact of outliers by parameterizing the conditional variance as a TS-GARCH model (see TS-GARCH) with the parameters estimated by least absolute deviations. where by definition. The FIREGARCH model allows for long-memory dependencies (see EGARCH and FIEGARCH). .i. A robust covariance matrix for the resulting Quasi MLE parameter estimates may be obtained by post. as long as the first two conditional moments of the model are correctly specified. The corresponding robust standard errors is sometimes referred to in the ARCH literature as Bollerslev-Wooldridge standard errors.d. A relatively simple-to-compute expression for this matrix involving only first derivatives was derived in Bollerslev and Wooldridge (1992). stable random variables. i. RGARCH1 (Randomized GARCH) The R-GARCH(r.q) model of Nowicka-Zagrajek and Weron (2001) replaces the intercept in the standard GARCH(p.p. . RGARCH3 (Root GARCH) The multivariate RGARCH model (see also MGARCH1 and StdevARCH) of Gallant and Tauchen (1998) is formulated in terms of the lower triangular N×N matrix . where the functions partitions the real line into J sub-intervals.q). where .e. and . QTARCH (Qualitative Threshold ARCH) The QTARCH(q) model of Gourieroux and Monfort (1992) assumes that the conditional variance may be represented by a sum of step functions: .q) model with a sum of r positive i. REGARCH (Range EGARCH) The REGARCH model of Brandt and Jones (2006) postulates an EGARCH type formulation for the conditional mean of the demeaned standardized logarithmic range.generally remain consistent and asymptotically normally distributed. model is readily defined by including p lagged conditional variances on the right-hand-side of the equation. so that equals unity th if falls in the j sub-interval and zero otherwise. The Generalized QTARCH. -25- . or LAD.and pre-multiplying the matrix of outer products of the gradients with an estimate of Fisher’s Information matrix.

Stoja and Tucker (2007) infers the conditional covariances through the estimation of auxiliary univariate GARCH models for the linear combinations in the identity. or realized variation. where is independent and identically distributed over time as a standard Stable Paretian distribution. GED-GARCH and NGARCH). SGARCH (Stable GARCH) Let . . the RGARCH formulation automatically guarantees that the resulting conditional covariance matrices are positive definite. RS-GARCH (Regime Switching GARCH) See SWARCH.. see. the formulation complicates the inclusion of asymmetries or “leverage effects” in the conditional covariance matrix. Sign-GARCH See GJR. A rapidly growing recent literature has been concerned with the use of such measures and the development of new and refined procedures in light of various data complications. Nothing guarantees that the resulting N×N conditional covariance matrix is positive definite (see also CCC and Flex-GARCH). RV (Realized Volatility) The term realized volatility. SARV (Stochastic AutoRegressive Volatility) See SV. S-GARCH (Simplified GARCH) The simplified multivariate GARCH (see MGARCH1) approach of Harris. e. The SGARCH model nests the ACH model (see ACH2) of McCulluch (1985) as a special case for . the review in Andersen. is commonly used in the ARCH literature to denote ex-post variation measures defined by the summation of within period squared or absolute returns over some non-trivial time interval. By parameterizing instead of . Many new empirical insights afforded by the use of daily realized volatility measures constructed from high-frequency intraday returns have also recently been reported in the literature. The Stable GARCH model for of Liu and Brorsen (1995) is then defined by: . -26- . However.g. Bollerslev and Diebold (2009).. and (see also GARCH-t.

diffusion analyzed by Heston (1993). Other exogenous explanatory variables may also be include in the equation for . Although Engle and Gonzalez-Rivera (1991) do not explicitly use the name SPARCH. When defined over increasingly finer sampling intervals. . . GED-GARCH and QMLE). or “structural. The Spline GARCH model was explicitly designed to investigate macroeconomic causes of slowly moving.” time series model in which one or more of the disturbances follow an ARCH model was dubbed a STARCH model by -27- . the SQR-GARCH formulation allows for closed form option pricing under reasonable auxiliary assumptions. and defines a partition of the full sample into k equally spaced time intervals. SQR-GARCH (Square-Root GARCH) The discrete-time SQR-GARCH model of Heston and Nandi (2000). as commonly found in the estimation of ARCH models (see also GARCH-t.SPARCH (SemiParametric ARCH) To allow for non-normal standardized residuals. Spline-GARCH The Spline-GARCH model of Engle and Rangel (2008) specifies the conditional variance of as the product of a standardized unit GARCH(1. the SQR-GARCH model converges weakly to the continuous-time affine. or low frequency volatility components (see also CGARCH1). is closely related to the VGARCH model of Engle and Ng (1993) (see VGARCH1). .1) model. In contrast to the standard GARCH(1. and a deterministic component represented by an exponential spline function of time. the approach has subsequently been referred to as such by several other authors in the literature. STARCH (Structural ARCH) An unobserved component. Engle and Gonzalez-Rivera (1991) suggest estimating the distribution of through non-parametric density estimation techniques. . where is equal to for and 0 otherwise.1) model. or square-root. The SQR-GARCH model is also sometime referred to as the Heston GARCH or the HestonNandi GARCH model (see also GARCH diffusion).

Ruiz and Sentana (1992). Structural GARCH The Structural GARCH approach named by Rigobon (2002) relies on a multivariate GARCH model for the innovations in an otherwise unidentified structural VAR to identify the parameters through time-varying conditional heteroskedasticity. so that the value of the function is bounded between 0 and 1 (see also ANST-GARCH. Strong GARCH GARCH models in which the standardized innovations.d. the SV approach has proven especially useful in the formulation of empirically realistic continuous-time volatility models of -28- . However.i. Meanwhile. or stochastic. This formulation obviously ensures that the conditional variance is positive. STGARCH (Smooth Transition GARCH) The ST-GARCH(1.Harvey. or SV model. discrete-time SV models are often formulated in terms of time series models for . where . are assumed to be i. through time are referred to as a strong GARCH models (see also Weak GARCH). refers to formulations in which is specified as a non-measurable.d. with mean zero and variance one. Stdev-ARCH (Standard deviation ARCH) The Stdev-ARCH(q) model first estimated by Schwert (1990) takes the form. the nonlinearity complicates the construction of forecasts from the model (see also AARCH). function of the observable information set. . Closely related ideas and models have been explored by Sentana and Fiorentine (2001) among others.i.1) model of Gonzalez-Rivera (1998) allows the impact of the past squared innovations to depend upon both the sign and the magnitude of through a smooth transition function. as exemplified by the simple SARV(1) model. . . . GJR and TGARCH). SV (Stochastic Volatility) The term stochastic volatility. To facilitate estimation and inference via linear state-space representations. where is i.

SWARCH (regime SWitching ARCH) The SWARCH model proposed independently by Cai (1994) and Hamilton and Susmel (1994) extends the standard linear ARCH(q) model (see ARCH) by allowing the intercept. the TGARCH(1. and the diffusive volatility coefficient is determined by a separate stochastic process (see also GARCH Diffusion). entering the conditional variance equation to depend upon some latent state variable.q) model proposed by Zakoian (1994) extends the TS-GARCH(p. or MS-GARCH. model. refers to a standard Brownian Motion. with the transition between the different states governed by a Markov chain.1) model may be expressed as: . or RS-GARCH. Tobit-GARCH The Tobit-GARCH model. -29- .q) model (see TS-GARCH) to allow the conditional standard deviation to depend upon the sign of the lagged innovations. or MGARCH.the form. In particular. models. TGARCH (Threshold GARCH) The TGARCH(p. . . extends the standard GARCH model (see GARCH) to allow for the possibility of censored observations on the ’s . where denotes the drift. Morgan and Trevor (1999) and Wei (2002). Different variants of these models are also sometimes refereed to in the literature as Markov Switching GARCH. . and/or the magnitude of the squared innovations. Jagannathan and Runkle (1993) (see GJR). or the underlying ’s. . Regime switching GARCH models were first developed by Gray (1996) (see GRS-GARCH). More general formulations allowing for multi-period censoring and related inference procedures been developed by Lee (1999). t-GARCH (t-distributed GARCH) See GARCH-t. first proposed by Kodres (1993) for analyzing futures prices. or exhibit jumps (see also SV and GARJI). or ZGARCH. or Mixture GARCH. The TGARCH model is also sometimes referred to as the ZARCH. Regime Switching GARCH. SVJ (Stochastic Volatility Jump) The SVJ acronym is commonly used to describe continuestime stochastic volatility models in which the sample paths may be dis-continuous. The basic idea behind the model is closely related to that of the GJR-GARCH model developed independently by Glosten.

in which the impact of the innovations for the conditional variance is symmetric and centered at . where . Higher order VGARCH(p. model. observations relative to the traditional GARCH(p. UGARCH (Univariate GARCH) See GARCH. To illustrate.q) models may be defined in a similar manner (see also AGARCH1 and NAGARCH). Unobserved GARCH See Latent GARCH. or NGARCH. The TS-GARCH model is also sometimes referred to as an Absolute Value GARCH. . in an absolute sense. It is a special case of the more general Power GARCH. Variance targeting has proven especially useful in multivariate GARCH modeling (see MGARCH1). or simply an AGARCH model. VCC (Varying Conditional Correlations) See DCC. -30- .1) model refers to the parameterization. or AVGARCH. Variance Targeting The use of variance targeting in GARCH models was first suggested by Engle and Mezrich (1996). formulation (see NGARCH).1) model (see GARCH).q) model (see GARCH).TS-GARCH (Taylor-Schwert GARCH) The TS-GARCH(p. . vech GARCH (vectorized GARCH) See MGARCH1. This formulation mitigates the influence of large. the VGARCH(1. consider the GARCH(1. Fixing at some pre-set value ensures that the long-run variance forecasts from the model converges to . TVP-Level (Time-Varying Parameter Level) See Level-GARCH.q) model of Taylor (1986) and Schwert (1989) parameterizes the conditional standard deviation as a distributed lag of the absolute innovations and the lagged conditional standard deviations. . VGARCH1 Following Engle and Ng (1993).

which is not formally closed under temporal aggregation.q) class of models. or concept. or portfolio formation (see also Strong GARCH). Similarly. as shown by Nijman and Sentana (1996) the unrestricted multivariate linear weak MGARCH(p.1) model of Fornari and Mele (1996) directly mirrors the GJR model (see GJR).q’) model. VSGARCH (Volatility Switching GARCH) The VSGARCH(1. -31- .VGARCH2 (Vector GARCH) The VGARCH. except that the asymmetric impact of the lagged squared negative innovations is scaled by the corresponding lagged conditional variance. . In the weak GARCH class of models is defined as the linear projection of on the space spanned by as opposed to the conditional expectation of . or (see also ARCH and GARCH).q) model remains a weak GARCH(p’. MGARCH and MV-GARCH acronyms are used interchangeably (see MGARCH1). In contrast to the standard GARCH(p.q) model (see MGARCH1) defined in terms of linear projections as opposed to conditional expectations is closed under contemporaneous aggregation. ZARCH (Zakoian ARCH) See TGARCH. the sum of successive observations from a weak GARCH(p. albeit with different orders p’ and q’. was first developed by Drost and Nijman (1993). Weak GARCH The weak GARCH class of models.

-32- .L. 58. Andersen. (2008). Kotz. 169-204. Christoffersen and F. and T. 7.O. “Multivariate GARCH Models: A Survey. 51.G.II . Bera. North Holland. “Interaction Between Autocorrelation and Conditional Heteroskedasticity: A Random-Coefficient Approach. 307-336. A.). Vol. “Volatility and Correlation Forecasting. Andersen. C. Bollerslev.” forthcoming in Y. 479-494. 74.J. Ltd.” Journal of Finance. and E. (1991). and M. 31.G. “ARCH Models: Properties. 123-130. Handbook of Economic Forecasting. Encyclopedia of Statistical Sciences.B.L. “Risk.” Journal of Economic Surveys. “Parametric and nonparametric Measurements of Volatility.Elliott and A. Bera. “Generalized Autoregressive Conditional Heteroskedasticity. Higgins (1993).G. C. Market Models: A Guide to Financial Data Analysis. Andersen. Lee (1992). Time-Varying Second Moments and Market Efficiency. Banks (eds). Higgins and S.” Journal of Econometrics. Bollerslev and H. Bollerslev and F. T. M. 305-366.. S.II: Practical Financial Econometrics.. Bollerslev.X. A. Handbook of Financial Econometrics. Granger. T. M.” Journal of Business and Economic Statistics. O.1): Applications to Excahnge Rate Modelling. 307-327. Laurent and J.” in C.L. T.X. Billio. Mikkelsen (1996). “ARCH and GARCH Models. T. “Return Volatility and Trading Volume: An Information Flow Interpretation of Stochastic Volatility.” Journal of Econometrics. Alexander.” Journal of Applied Econometrics.K. “Fractionally Integrated Generalized Autoregressive Conditional Heteroskedasticity. C.References Alexander. Read and D. Vol. 79-110.. (1986).K.. Amsterdam: North-Holland.P Hansen (eds.” Review of Economic Studies. Gobbo (2006).K. Estimation and Testing. T.V. P.” Applied Financial Economics Letters. Bollerslev (1998). R. T. Baillie. Diebold (2006).” in S. T. Attanasio. Lazar (2006). “Flexible Dynamic Conditional Correlation Multivariate GARCH Models for Asset Allocation. 2. (2001). Andersen. Alexander. 21. (1996). “Normal Mixture GARCH(1.W. 3-30. 133-142. Rombouts (2006). Chichester. Aït-Sahalia and L. 777-878. G. 21. UK: John Wiley and Sons. C.. L. Market Risk Analysis. T.” Journal of Applied Econometrics. Bauwens. Timmermann (eds).G. M.. 10. Diebold (2009). UK: John Wiley and Sons. Chichester. Caporin and M.T. New York: John Wiley and Sons. Ltd.

P. “Continuous-Time GARCH Processes. 96. Bollerslev. Princeton: Princeton University Press.Bollerslev. “A Conditionally Heteroskedastic Time Series Model for Speculative Prices and Rates of Return.” Econometric Reviews. “Periodic Autoregressive Conditional Heteroskedastcity.S.. -33- . 309-316. R. Chou and K. “A Markov Model of Switching-Regime ARCH. R. Chadraa and A. 2959-3038. Amsterdam: North-Holland. T. “A Capital Asset Pricing Model with Time Varying Covariances.” Journal of Business and Economic Statistics.). “Asymmetric Dynamics in the Correlations of Global Equity and Bond Returns. T. 537-572. M.M. 12.J.burns-stat. Bollerslev. Nelson (1994). 5-59.” Journal of Financial Harjes and K. (2005). T. and E. E. Cai. L. and M.F.” Journal of Business and Economic Statistics. 385-412. 4. “Quasi-Maximum Likelihood Estimation and Inference in Dynamic Models with Time Varying Covariances. McAleer (2006). 790-826.. Brandt. Engle and D. R.” Journal of Political Economy. Sheppard (2006). T.W. Brenner. Bollerslev. Bollerslev.H. Handbook of Econometrics. Engle and K. 31.. R. R. and J.F. J. “Another Look at Models of the Short-Term Interest Rate. Kroner (1996). 11. Wooldridge (1988). T. UK: Cambridge University Press. McFadden (eds.” in R. “Dynamic Asymmetric GARCH. Caporin. 542-547. Ghysels (1996).F. 72. Cappiello. 4. “Multivariate GARCH with Only Univariate Estimation.Y. 470-486. (1994).” http://www.” Review of Economics and Statistics. Bollerslev.” Journal of Financial and Quantitative Analysis. Engle and J. Brooks. T.F. M. MacKinlay (1997) The Econometrics of Financial Markets. “Volatility Forecasting with Range-Based EGARCH Models. Bollerslev. Wooldridge (1992). Cambridge. (2002) Introductory Econometrics for Finance. T.” Review of Economics and Statistics. (1990). 139-151. “ARCH Models. 143-172. Campbell. Brockwell. Kroner (1992). Volume IV. Engle and D. 14.” Annals of Applied Probability. Burns. Jones (2006)..W. and C.” Journal of Business and Economic Statistics.Y. J. 16.. R. 24.F. “Modeling the Coherence in Short-Run Nominal Exchange Rates: A Multivariate Generalized ARCH Model. 498-505. 116-131. Lindner (2006).B.” Journal of Financial Econometrics. P.M.” Journal of Econometrics. 52. 69.F. Lo and A. “ARCH Modeling in Finance: A Selective Review of the Theory and Empirical Evidence..C. C. (1987). 85-107. A.

H. C.J. Engle (1993).” Econometrica. Clark. Asymmetric and Hysteresis in Stock Returns: International Evidence. Z. Engle. F. Diebold. (2004). Kamstra (1997). (1973). and T. and M.A. 4. (2003) Elements of Financial Risk Management. 1. “Modeling Volatility Dynamics. “Pricing of Permanent and Transitory Volatility for U. 427-472. F. Den Hertog. Satchell (2002). Ding. 135-156. “The Impulse Response Function of the Long Memory GARCH Process. 271-324. (1994).” Economic Letters.E. 1-21. Rockinger (1997). Granger and R. P. 4. 37. New York: John Wiley and Sons.” Journal of Applied Econometrics. Diebold. Boston: Kluwer Academic Press. 4. Credit and Banking. and M. Christodoulakis.” Journal of Business and Economic Statistics. “Autoregressive Conditional Heteroscedasticity (ARCH) Models: A Review. P. Tensions and Prospects. Donaldson.J. Lopez (1995). (2004). and J. 16-29. “Volatility Clustering.H. “Forecasting Financial Volatilities with Extreme Values: The Conditional Autoregressive Range (CARR) Model. (2005).K.Y.” in K.G. F.F. F. Karanasos (2006). Christoffersen.” Quality Technology and Quantitative Management. R. Nijman (1993).X. 421-426.” Journal of Empirical Finance.W. “The Dynamics of Exchange Rate Volatility: A Multivariate Latent Factor ARCH Model.G. and E. Macroeconometrics: Developments. 1. Davidson. 561-582. R. 41.Chan.” European Journal of Operational Research. “A Long Memory Property of Stock Market Returns and a New Model.” Economic Letters.” Financial Engineering and the Japanese Markets. San Diego: Academic Press. Diebold. S. Inc.” Journal of Money.E.” Econometrica. 44. and M. 22. 34-41.). J.X. Xekalaki (2004). and M. Stock Returns: A Composite GARCH Model. 106. Drost. 351-370. Nerlove (1989). 1-35. and a New Model.. 165-185. Degiannakis. -34- . N. Chou. Conrad. (2002) Time Series: Applications to Finance.C. “Temporal Aggregation of GARCH Processes. G. R.S. 139. 83-106.” Scandinavian Journal of Economics. 90. and S. Hoover (ed. “The Nobel Memorial Prize for Robert F. “Correlated ARCH (CorrARCH): Modelling TimeVarying Conditional Correlation Between Financial Asset Returns.F. 909-927. Crouhy. “A Subordinated Stochastic Process Model with Finite Variance for Speculative Prices.X. 61. “Moment and Memory Properties of Linear Conditional Heteroskedasticity Models. “An Artificial Neural Network GARCH model for International Stock Return Volatility.” Journal of Empirical Finance. 17-46. C.

Oxford. R. “Dynamic Conditional Correlation: A Simple Class of Multivariate GARCH Models. “Estimating Time Varying Risk Premia in the Term Structure: The ARCH-M Model.G. Hoboken.F.F. 405-420. “Autoregressive Conditional Heteroskedasticity with Estimates of the Variance of U.” Econometrica. 9. 3. Engle. (2004). 391-407. Engle.” in R. Engle. and S.” Journal of Econometrics.J. R. Kroner (1995). R. “Modeling the Persistence of Conditional Variances. (2002a).” American Economic Review. “New Frontiers for ARCH Models.” Journal of Business and Economic Statistics. Mezrich (1996). Engle.F. “Augmented GARCH(p.F. 345-359. Enders. 97-127.F. (2002b). White (eds. R. Oxford. 94. 50. 987-1008. R. R. Engle.q) Process and its Diffusion Limit. 157-168. Engle. 22. (2001). and G.F. Manganelli (2004). Engle.F. Inflation. W.K. Risk and Volatility: Econometric Models and Financial Practice. R. Causality.” Risk. 36-40. R. and Forecasting: A Festschrift in Honor of Clive W. “CAViaR: Conditional Autoregressive Value-at-Risk by Regression Quantiles.P. R.” Journal of Business and Economic Statistics. Robbins. Engle. Engle. 11. Engle. R.F. (1982). and G. Cointegration. 79. 17. (1990). Inc. Granger.F. 425446. and T. Engle.K. 20.” Econometrica. “GARCH 101: The Use of ARCH/GARCH Models in Applied Econometrics.” Journal of Applied Econometrics. 5. Gonzalez-Rivera (1991). and J..J. Engle.” Econometric Theory. UK: Oxford University Press. Bollerslev (1986). 475-497.” Journal of Business and Economic Statistics. “Semiparametric ARCH Models. and F. 339-350. UK: Oxford University Press. 9. (1995) ARCH: Selected Readings.F. D. Lee (1999). “Discussion: Stock Market Volatility and the Crash of ‘87.). 1-50. R. “Nobel Lecture. (1997). “GARCH for Groups. Engle. NJ: John Wiley and Sons. “A Permanent and Transitory Component Model of Stock Return Volatility. (1987).Duan.F. 55.” Review of Financial Studies. -35- . 15.F. “Multivariate Simultaneous Generalized ARCH. R. R.” Econometric Reviews.F. 367-381.F. Engle and H. J. R.” Journal of Economic Perspectives.M. 122-150. 103-106.F. Engle. (2004) Applied Econometric Time Series. Lilien and R.

Engle. R.R.R. R. “What Good is a Volatility Model?” Quantitative Finance. R. Laibson and H. Engle.. 72. P. 48. Tauchen (1998). (1998).F.” Journal of Derivatives.. “SNP: A Program for Nonparametric Time Series Analysis. Franses. Shephard (2004).” Review of Financial Studies. 1187-1221. Gourieroux. Nelson (1996). van Dijk (2000) Non-Linear Time Series Models in Empirical Finance.econ. 50. Geweke. and G. A. Cambridge. 1749-1778.R.” Journal of Econometrics. 137-189. Rothschild (1990).” Econometrica. 61-78. “Modeling the Changing Asymmetry of Conditional Variances” Economics Letters.M. “The Spline-GARCH Model for Low Frequency Volatility and its Global Macroeconomic Causes. Fiorentini. D. 3. “Asset Pricing with a Factor-ARCH Covariance Structure: Empirical Estimates for Treasury Bills. C. 1481-1517.” Brookings Papers on Economic Activity. Rangel (2008). and J. Glosten. Jasiak (2001) Financial Econometrics. R.Engle. Mele (1996). 1127-1162. Gallant.F. Foster. (1986). Friedman. Engle. R. 64. 197-203. Minsky (1989). 1. Sentana and N. “Modeling the Persistence of Conditional Variances: A Comment. “On the Relation Between the Expected Value and the Volatility of the Nominal Excess Return on Stocks. D. and J.F.F.” Econometric Review.B. and J. Gonzalez-Rivera.” Econometrica.F.K. 229-247. Ng and M.” an online guide available at www. 213-238.F. R. 57-61. “Likelihood-Based Estimation of Latent Generalized ARCH Structures. Runkle (1993).html. Engle. Fornari. and A. Ng (1993). and D. and A. UK: Cambridge University Press. -36- . E.P. NJ: Princeton University Press.duke. “Economic Implications of Extraordinary Movements in Stock Prices.I. G.. 66. 17. L. Engle.K.J. 1779-1801. Rosenberg (1995). “Measuring and Testing the Impact of News on Volatility. Russell (1998). 5. F. Princeton.G. Jagannathan and D. Patton (2001). J. 45. 237245. “GARCH Gamma. “Autoregressive Conditional Duration: A New Model for Irregularly Spaced Transaction Data.” Journal of Finance. V. and V. “Smooth Transition GARCH Models.” Econometrica. and J.H. and D. R. 21..” Journal of Finance. 48. “Continuous Record Asymptotics for Rolling Sample Estimators.” Studies in Nonlinear Dynamics and Econometrics. B. 139-174.

J. C. E. Granger. Bera (1992).D. (1983). 465-487. 64. Princeton. 275-292. “Probabilistic Properties of the β-ARCH Model. “Acronyms in Time Series Analysis (ATSA). 39. Hentschel. Harvey. 34. Tucker (2007).” Journal of Financial Economics.L. “A Model of the Federal Funds Rate Target. C. R. and A. “Autoregressive Conditional Heteroskedasticity and Changes in Regimes. (1994). Park (2008). C. J. Han. J. E.” International Economic Review. 307-333. Jordá (2002). “Autoregressive Conditional Skewness. -37- .” Journal of Financial and Quantitative Analysis.L. D.” Journal of Applied Probability. and A.” Journal of Political Economy. Harris.. 575-598. 52. Hamilton. 110.D. “Qualitative Threshold ARCH Models.F. “Autoregressive Conditional Density Estimation. And J.” Journal of Econometrics. (1994) Time Series Analysis. Susmel (1994). Gray.” Review of Financial Studies.W. 146. L. 35. 327-343. Hamilton. J. 129-157. S. Harvey. 159-199.” Journal of Financial Economics. S. 27-62. “A Closed-Form Solution for Options with Stochastic Volatility. and R.” Journal of Econometrics. 42.. Higgins. “Modeling the Conditional Distribution of Interest Rates as a Regime-Switching Process. Ruiz and E. 705-730.E.” International Economic Review.R.Gourieroux. 103-107. and A.F. Stoja and J. “All in the Family: Nesting Symmetric and Asymmetric GARCH Models. Siddique (1999). (1996).” Journal of Futures Markets. B. Hansen. 4. M. 6. NJ: Princeton University Press. Haug. 33. “A Class of Nonlinear ARCH Models. (1993). and O.” Statistica Sinica. Hamilton. H. with Applications to Bond and Currency Options. 52.” Journal of Econometrics.” Journal of Econometrics. “A Simplified Approach to Modeling the Comovement of Asset Returns. “Unobserved Component Time Series Models with ARCH Disturbances. Heston. A. and J.K. 27. (1995).1135-1167.D. “An Exponential Continuous-time GARCH Process. Diebolt (1994). 137-158. And C. 960-976. S. 71-104. Monfort (1992). 44.Y. Czado (2007). 71-87. 3.” Journal of Time Series Analysis. “Time Series Properties of ARCH Processes with Persistent Covariates. Guégan. Sentana (1992).

Santa-Clara and M. A. “Asymptotic Theory for ARCH-SM Models: LAN and Residual Empirical Processes.W. “A Continuous Time GARCH Process Driven by a Lévy Process: Stationarity and Second Order Behaviour. S. Serna (2005). 29-52. and B. “Asymptotic Theory for the GARCH(1. 65. 585-625. Maller (2004). 134.” Econometric Theory.” Journal of Business.. B. “Autoregessive Conditional Volatility. 355390. 15. Á. S. (1994).” Journal of International Money and Finance. -38- . E. 199-219. “GARCH Model with Cross-Sectional Volatility: GARCHX Models. G.” Quarterly Review of Economics and Finance. Taniguchi (2005). Lindner and R. Hansen (1994).E.” Journal of International Money and Finance. P.” Statistica Sinica.” Journal of Applied Econometrics.. and W. and S. S.F.” Journal of Business.1) Quasi-Maximum Likelihood Estimator. L. and M. Ledoit O. 66. LeBaron. Lee. S. 735-747. C. “Estimation of Dynamic and ARCH Tobit Models. 601-622. Lee. Lee. 463-490. C. “The Copula-GARCH Model of Conditional Dependencies: An International Stock Market Application. 13. 253-274. Lee.. Hwang.L. and M. “Flexible Multivariate GARCH Modeling with an Application to International Stock Markets. (1993). “Some Relations between Volatility and Serial Correlation in Stock Market Returns. Klüppelberg. Satchell (2005). 203-216.” Applied Financial Economics. “A Closed-Form GARCH Option Valuation Model. León. 45. and B. 92. Skewness and Kurtosis. “Matrix Exponential GARCH. “On a Double Threshold Autoregressive Heteroskedastic Time Series Model. Li. Jondeau.” Review of Financial Studies. Li (1996).” Journal of Econometrics. Kawakatsu.H. H.E.E. (1992). Liu.K. 215-234. Rockinger (2006). 11. “Maximum Likelihood Estimation of a GARCH Stable Model. L. 13.” Journal of Applied Econometrics. 85. 15. (2006). Brorsen (1995). T. 375-382. 95-128.Heston. 10.W.” Journal of Econometrics.W. 41. Wolf (2003). Nandi (2000). 10. Rubio and G. and S.” Journal of Applied Probability.M.” Review of Economics and Statistics. “Spread and Volatility in Spot and Forward Exchange Rates. Kodres. S. 272-285. 827853. “Test of Unbiasedness in Foreign Exchange Futures Markets: An Examination of Price Limits and Conditional Heteroskedasticity. (1999). 599-618. 25.

von Weizsäcker (1997). Nelson.G.B.” Journal of Business and Economic Statistics.” Journal of Banking and Finance. and J. 1-47. D. 347-370. R. Cambridge. U. 318-334. Puctet.D. (1990a). Olsen. “Modeling Multiple Regimes in Financial Volatility with a Flexible Coefficient GARCH(1. Frey (2000). D. D. (1996). “Interest-Risk Sensitive Deposit Insurance Premia: Stable ACH Estimates.” Econometrica. “Volatilities of Different Time Resolutions .1) Models. “Conditional Heteroskedasticity in Asset Returns: A New Approach. 64. M.B. (1993) The Econometric Modelling of Financial Time Series.H. 117-161. (1996b). and R. R. McNeil.B. 137-156. A.” Journal of Empirical Finance. “Consistency and Asymptotic Normality of the Quasi-Maximum Likelihood Estimator in GARCH(1. 739. Nelson.” Journal of Econometrics. 7. (1985). 61-90. Pyun and A. 25..” Econometrica. Nam. 64.B.G. 59.J. “Limit Moves as Censored Observations of Equilibrium Futures Prices in GARCH Processes. (1996a). Davé. Veiga (2009).C.M. Medeiros.C. Mills.” Econometrica. (1992). D. 561-573. “Asymptotic Filtering Theory for Multivariate ARCH Models. Nelson.C.” Econometric Theory.B.1) Model. D. I.1) and Covariance Stationary GARCH(1. “A Multiplicative Parameterization of ARCH Models.” working paper. Nelson. “Asymmetric Mean-Reversion and Contrarian Profits: ANST-GARCH Approach.A. 397-408. 45. (1991). 4. “Estimation of Tail-Related Risk Measures for Heteroskedastic Financial Time Series: An Extreme Value Approach.. 271300. 9. Nelson. and A. “Filtering and Forecasting with Misspecified ARCH Models I: Getting the Right Variance with the Wrong Model. Müller. J. O.” Econometric Theory.” Journal of Econometrics. Dacorogna. Milhøj. 563-588.B. (1987). -39- . 71. A. T.Analyzing the Dynamics of Market Components. Trevor (1999). Morgan. Nelson.” Journal of Empirical Finance. M. D.Lumsdaine.” Journal of Empirical Finance. Department of Statistics. and R. 575-596. McCulloch.L.” Journal of Econometrics. 52.. C.B.S. 213-239. 17.V. University of Copenhagen. 9. K. Arize (2002). “Asymptotically Optimal Smoothing with ARCH Models. (1990b). “ARCH Models as Diffusion Approximations. R.1) Model. “Stationarity and Persistence in the GARCH(1. 6. UK: Cambridge University Press.

R. (2006). S. Poon. Cao (1992). Volume 14.” Journal of Business and Economic Statistics. Sentana. (1986). 371-380.R. Nelson. E. T. Ltd. A. 5. Maddala (eds. 102. 1-41. and C. Robinson. Sentana.J. “The Curse of Non-Investment Grade Countries. A.B. “Modelling Asymmetric Exchange Rate Dependence. (1996). G. (1991). (1989). Palm. 639-661. 62.” Econometric Review. 423-449. “Dependence Structure of Stable R-GARCH Processes. and D.H.” Review of Economic Studies. (2002). “Inequality Constraints in the Univariate GARCH Model. 67-84. 71. Nijman. “GARCH Models of Volatility. Sentana (1996). S.Q.” International Economic Review. “Stock Volatility and the Crash of ‘87. B. Rao and G. Foster (1994). Chichester. Fiorentini (2001). 21. (1995). (2005) A Practical Guide to Forecasting Financial Market Volatility.” Econometrica.” Journal of Development Economics.” Probability and Mathematical Statistics. 143-164. 381-393. P. 10. “Asymptotic Filtering Theory for Univariate ARCH Models. 71-87.” Journal of Empirical Finance. 3. UK: John Wiley & Sons.S. D.G. 21.J.” Journal of Econometrics. 47. 229-235. “Identification. “Modeling the Persistence of Conditional Variances: A Comment. “The Econometrics of Financial Markets. 15-102. 3. D.Nelson.W. G.” Review of Financial Studies. 1115-1153.” Journal of Econometrics.) Handbook of Statistics. Pagan. “An Outlier Robust GARCH Model and Forecasting Volatility of Exchange Rate Returns. Patton. Schwert. -40- . E. Werron (2001). F. “Testing for Strong Serial Correlation and Dynamic Conditional Heteroskedasticity in Multiple Regression. Rigobon. Park. Pantalu. 527-556. Nowicka-Zagrajek J. 62. 209-240. and G. Estimation and Testing of Conditional Heteroskedastic Factor Models.W.” Journal of Forecasting. and E. (1996). “Marginalization and Contemporaneous Aggregation in Multivariate GARCH Processes.” Journal of Econometrics.B. (1990).” in C. Amsterdam: North-Holland. 69.M. 71-74. 47. “Why Does Stock Market Volatility Change Over Time?” Journal of Finance. (2002). Schwert. 77-102. and A. “Quadratic ARCH Models. 44.

E. Li (2001). J. S. 197-223. 549-564.” in D. 49.K.S.K. Wong. J. 20. Tsay.C. UK: John Wiley and Sons. Princeton.” Economics Letters. and W.” Econometrica. 96. 367-372. 49-55.” Journal of Empirical Finance. R.” Journal of Economic Dynamics and Control. (1998). K. (1994). (2002). -41- . 27.” Journal of Business and Economic Statistics. Yang.S. Taylor. Cox. Zakoïan. Y. Van der Weide.” Journal of Applied Econometrics. C. and R.V. Tauchen. 577-597. “Moving Average Conditional Heteroskedastic Processes. 17. “Threshold Heteroskedastic Models. “The Price Variability-Volume Relationship on Speculative Markets. Finance and Other Fields.J. 549-564. Tsui (2002).” Journal of Time Series Analysis. Watson (2003) Introduction to Econometrics. Y. Yuen (2006).K. and M. (1996).H. Pitts (1983). Tse. London: Chapman & Hall.” Journal of the American Statistical Association. Wei. NJ: Princeton University Press. N.R.J.Shephard. Inc. W. M. R. S.J. Boston: Addison Wesley. Chichester. “Statistical Aspects of ARCH and Stochastic Volatility Models. 351-362. “On a Mixture GARCH Time Series Model. Hinkley and O. “GO-GARCH: A Multivariate Generalized Orthogonal GARCH Model. “The Conditional Heteroskedasticity of the Yen-Dollar Exchange Rate. D. G. 485-505. van der (2002). 931-955. New York: John Wiley and Sons. Barndorff-Nielsen (eds.-M. 17. 13. Stock. Weide.K.C.” Journal of Applied Econometrics.” Journal of Applied Econometrics. 9. 1-67.. (2002) Analysis of Financial Time Series. (2002).) Time Series Models in Econometrics. 51.W. (2004) Asset Price Dynamics and Prediction. “On a Mixture Autoregressive Conditional Heteroskedastic Model. (1986) Modeling Financial Time Series. (2006) Empirical Dynamic Asset Pricing. Tse. Princeton: Princeton University Press. Singleton. 982-995. S. and A. 18. Zhang. Z. R. “A Censored-GARCH Model of Asset Returns with Price Limits. Taylor.X. “GO-GARCH: A Multivariate Generalized Orthogonal GARCH Model. Keung and K. and M. Bewley (1995). “A Multivariate GARCH Model with Time-Varying Correlations.

Sign up to vote on this title
UsefulNot useful