Timo Teräsvirta

Specification, Estimation, and Evaluation of Smooth Transition Autoregressive Models

Abstract This article considers the application of two families of nonlinear autoregressive models, the logistic (LSTAR) and exponential (ESTAR) autoregressive models. This includes the specification of the model based on simple statistical tests: linearity testing against smooth transition autoregression, determining the delay parameter and choosing between LSTAR and ESTAR models are discussed. Estimation by nonlinear least squares is considered as well as evaluating the properties of the estimated model. The proposed techniques are illustrated by examples using both simulated and real time series.

Smooth transition autoregressive models - a survey of recent developments

This paper surveys recent developments related to the smooth transition autoregressive (STAR) time series model and several of its variants. We put emphasis on new methods for testing for STAR nonlinearity, model evaluation, and forecasting. Several useful extensions of the basic STAR model, which concern multiple regimes, time-varying non-linear properties, and models for vector time series, are also reviewed.

Testing the adequacy of smooth transition autoregressive models

Smooth transition autoregressive models are a flixible family of nonlinear time series models that have also been used for modelling economic data. This paper contributes to the evaluation stage of a proposed specification, estimation, and evaluation cycle of this models by introducing a Lagrange multiplier (LM) test for the hypothesis of no error autocorrelation and LM type tests for the hypothesis of remaining nonlinearity and that of parameter constancy. Small sample properies of the F versions of the tests and some alternative tests are investigated by simulation. The results indicate that the proposed tests can be applied in small samples already.

Multivariate GARCH models

This article contains a review of multivariate GARCH models. Most common GARCH models are presented and their properties considered. This also includes nonparametric and semiparametric models. Existing specification and misspecification tests are discussed. Finally, there is an empirical example in which several multivariate GARCH models are fitted to the same data set and the results compared.

Testing the constancy of regression parameters against continuous structural change

Abstract A standard explicit or implicit assumption underlying many parameter constancy tests in linear models is that there is a single structural break in the sample. In this paper that assumption is replaced by a more general one stating that the parameters of the model may change continuously over time. The pattern of change is parameterized giving rise to a set of parameter constancy tests against a parameterized alternative. The power properties of the LM type tests in small samples are compared to those of other tests like the CUSUM and Fluctuation Test by simulation and found very satisfactory. An application is considered.

Stylized facts of daily return series and the hidden Markov model

In two recent papers, Granger and Ding (1995a,b) considered long return series that are first differences of logarithmed price series or price indices. They established a set of temporal and distributional properties for such series and suggested that the returns are well characterized by the double exponential distribution. The present paper shows that a mixture of normal variables with zero mean can generate series with most of the properties Granger and Ding singled out. In that case, the temporal higher-order dependence observed in return series may be described by a hidden Markov model. Such a model is estimated for ten subseries of the well-known S&P 500 return series of about 17,000 daily observations. It reproduces the stylized facts of Granger and Ding quite well, but the parameter estimates of the model sometimes vary considerably from one subseries to the next. The implications of these results are discussed.

Properties of Moments of a Family of GARCH Processes

This paper considers the moments of a family of first-order GARCH processes. First, a general condition of the existence of any integer moment of the absolute values of the observations is given. Second, a general expression for this moment as a function of lower-order moments is derived. Third, the kurtosis and the autocorrelation function of the squared and absolute-valued observations are derived. The results apply to a host of different GARCH parameterizations. Finally, the existence, or the lack thereof, of a theoretical counterpart to the so-called Taylor effect for some members of this GARCH family is discussed. Possibilities of extending some of the results to higher-order GARCH processes are indicated and potential applications of the statistical theory proposed.

A simple nonlinear time series model with misleading linear properties

This paper shows how a simple univariate stationary nonlinear process has an autocorrelation function suggesting that the underlying process has a long memory, although that is not the case. The conclusion is that just considering linear properties of a process may be misleading.

Time-Varying Smooth Transition Autoregressive Models

Nonlinear regime-switching behavior and structural change are often perceived as competing alternatives to linearity. In this article we study the so-called time-varying smooth transition autoregressive (TV-STAR) model, which can be used both for describing simultaneous nonlinearity and structural change and for distinguishing between these features. Two modeling strategies for empirical specification of TV-STAR models are developed. Monte Carlo simulations show that neither of the two strategies dominates the other. A specific-to-general-to-specific procedure is best suited for obtaining a first impression of the importance of nonlinearity and/or structural change for a particular time series. A specific-to-general procedure is most useful in careful specification of a model with nonlinear and/or time-varying properties. An empirical application to a large dataset of U.S. macroeconomic time series illustrates the relative merits of both modeling strategies.

Evaluating GARCH models

This paper suggests a unified framework for testing the adequacy of anestimated GARCH model. Nothing more complicated than standard asymptotictheory is required. Parametric tests of no ARCH in standardized errors,symmetry, and parameter constancy are suggested. Estimating the alternativewhen the null hypothesis is rejected may give useful ideas of how to improvethe specification. It is also shown that the recent portmanteau test of Liand Mak (1994) is asymptotically equivalent to our test of no ARCH in thestandardized error process.