Generalized Autoregressive Score Models with Applications

Department of Finance, VU University Amsterdam, and Duisenberg School of Finance, Amsterdam, Netherlands
Journal of Applied Econometrics (Impact Factor: 1.76). 08/2013; 28(5). DOI: 10.1002/jae.1279


We propose a class of observation-driven time series models referred to as generalized autoregressive score (GAS) models. The mechanism to update the parameters over time is the scaled score of the likelihood function. This new approach provides a unified and consistent framework for introducing time-varying parameters in a wide class of nonlinear models. The GAS model encompasses other well-known models such as the generalized autoregressive conditional heteroskedasticity, autoregressive conditional duration, autoregressive conditional intensity, and Poisson count models with time-varying mean. In addition, our approach can lead to new formulations of observation-driven models. We illustrate our framework by introducing new model specifications for time-varying copula functions and for multivariate point processes with time-varying parameters. We study the models in detail and provide simulation and empirical evidence. Copyright © 2012 John Wiley & Sons, Ltd.

Download full-text


Available from: Andre Lucas, Oct 05, 2015
107 Reads
  • Source
    • "The authors find a significantly time-varying correlation between euro/US dollar and yen/US dollar, dependent on the past return realizations. Creal et al. (2013) further introduced a a generalized autoregressive score model to facilitate time-varying distributions using the lagged score of the density as the forcing variable in the dynamic. However, the UIP puzzle introduced in Section 2 has not been explored in the literature from a copula modelling approach. "
    [Show description] [Hide description]
    DESCRIPTION: The uncovered interest rate parity puzzle questions the economic relation existing between short term interest rate differentials and exchange rates. One would indeed expect that the differential of interest rates between two countries should be offset by an opposite evolution of the exchange rate between them, hence ruling out any limited risk profit opportunities. However, it has been shown empirically that this relation is not holding and accordingly has led, over the past two decades, to the reinforcement of a well-known trading strategy in financial markets, namely the currency carry trade. This paper investigates how highly leveraged, mass speculator behaviour affects the dependence structure of currency returns. We propose a rigorous statistical modelling approach using two complementary techniques in order to demonstrate that speculative carry trade volumes are informative in both the covariance and tail dependence of high and low interest rate currency returns, whereas the price based factors previously suggested in the literature hold little explanatory power. We add a new feature to the understanding of the link between the UIP condition and the carry trade strategy, specifically attributed to the large joint exchange rate movements in high and low risk environments.
  • Source
    • "The alternative class of observation-driven models, by contrast, allows parameters to vary over time as functions of lagged dependent variable values and exogenous variables. By way of an example, the recently introduced Generalized Autoregressive Score (GAS) models (Creal et al., 2013), also known as Dynamic Conditional Score (DCS) models, also provide a general framework for modelling time variation in parametric models as functions of lagged dependent variables and exogenous variables (see also Creal et al., 2011). Thus, the GAS model is an observation-driven time series model assuming that we can compute the score of the parametric conditional observation density with respect to the time varying parameter. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In many settings of empirical interest, time variation in the distribution parameters is important for capturing the dynamic behaviour of time series processes. Although the fitting of heavy tail distributions has become easier due to computational advances, the joint and explicit modelling of time-varying conditional skewness and kurtosis is a challenging task. We propose a class of parameter-driven time series models referred to as the generalized structural time series (GEST) model. The GEST model extends Gaussian structural time series models by a) allowing the distribution of the dependent variable to come from any parametric distribution, including highly skewed and kurtotic distributions (and mixed distributions) and b) expanding the systematic part of parameter-driven time series models to allow the joint and explicit modelling of all the distribution parameters as structural terms and (smoothed) functions of independent variables. The paper makes an applied contribution in the development of a fast local estimation algorithm for the evaluation of a penalised likelihood function to update the distribution parameters over time without the need for evaluation of a high-dimensional integral based on simulation methods.
  • Source
    • "For other possible choices of a we refer to Creal et al. (2013). "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper compares the Value--at--Risk (VaR) forecasts delivered by alternative model specifications using the Model Confidence Set (MCS) procedure recently developed by Hansen et al. (2011). The direct VaR estimate provided by the Conditional Autoregressive Value--at--Risk (CAViaR) models of Eengle and Manganelli (2004) are compared to those obtained by the popular Autoregressive Conditional Heteroskedasticity (ARCH) models of Engle (1982) and to the recently introduced Generalised Autoregressive Score (GAS) models of Creal et al. (2013) and Harvey (2013). The Hansen's procedure consists on a sequence of tests which permits to construct a set of "superior" models, where the null hypothesis of Equal Predictive Ability (EPA) is not rejected at a certain confidence level. Our empirical results, suggest that, after the Global Financial Crisis (GFC) of 2007-2008, highly non-linear volatility models deliver better VaR forecasts for the European countries as opposed to other regions. The R package MCS is introduced for performing the model comparisons whose main features are discussed throughout the paper.
Show more