|
on Econometric Time Series |
| By: | Andres M. Alonso; Elizabeth A. Maharaj |
| Abstract: | In this paper we propose a procedure based on the subsampling techniques for the comparison of stationary time series that are not necessarily independent. We study a test based on the Euclidean distance between the autocorrelation functions of two series. Consistency of the proposed method is established. We present a Monte Carlo study with the size and the power of the proposed test. |
| Date: | 2005–02 |
| URL: | http://d.repec.org/n?u=RePEc:cte:wsrepe:ws050702&r=ets |
| By: | Takamitsu Kurita (Dept of Economics, University of Oxford); Bent Nielsen (Dept of Economics, University of Oxford) |
| Abstract: | This paper addresses the question of whether a conventional approach to cointegration is applicaple to the case where changes are allowed in the parameters for the short term dynamics. We reparametrise a vector autoregressive model such that the short-run parameters exhibiting changes at known points are explicitly given. We then show that the likelihood ratio test statistic for cointegration rank is based on reduced rank regression and has the usual asymptotic distribution. An empirical illustration using US gasoline prices is presented. |
| Date: | 2005–01–01 |
| URL: | http://d.repec.org/n?u=RePEc:nuf:econwp:0501&r=ets |
| By: | Juan Carlos Escanciano Reyero (School of Economics and Business Administration, University of Navarra) |
| Abstract: | In this article we study a general class of goodness-of-fit tests for the conditional mean of a linear or nonlinear time series model. Among the properties of the proposed tests are that they are suitable when the conditioning set is infinite-dimensional; are consistent against a broad class of alternatives including Pitman's local alternatives converging at the parametric rate ; and do not need to choose a lag order depending on the sample size or to smooth the data. It turns out that the asymptotic null distributions of the tests depend on the data generating process, so a new bootstrap procedure is proposed and theoretically justified. The proposed bootstrap tests are robust to higher order dependence, in particular to conditional heteroskedasticity of unknown form. A simulation study compares the finite sample performance of the proposed and competing tests and shows that our tests can play a valuable role in time series modeling. Finally, an application to an economic price series highlights the merits of our approach. |
| JEL: | C12 |
| Date: | 2005–02 |
| URL: | http://d.repec.org/n?u=RePEc:una:unccee:wp0205&r=ets |
| By: | Carl Chiarella (School of Finance and Economics, University of Technology, Sydney); Thuy-Duong To (School of Finance and Economics, University of Technology, Sydney) |
| Abstract: | This paper seeks to estimate a multifactor volatility model so as to describe the dynamics of interest rate markets, using data from the highly liquid but short term futures markets. The difficult problem of estimating such multifactor models is resolved by using a genetic algorithm to carry out the optimization procedure. The ability to successfully estimate a multifactor volatility model also eliminates the need to include a jump component, the existence of which would create difficulties in the practical use of interest rate models, such as pricing options or producing forecasts. |
| Keywords: | term structure; volatility; mutlifactor; jump; eurodollar futures; genetic algorithm |
| JEL: | C51 C61 E43 |
| Date: | 2005–01–01 |
| URL: | http://d.repec.org/n?u=RePEc:uts:rpaper:150&r=ets |
| By: | Carl Chiarella (School of Finance and Economics, University of Technology, Sydney); Shenhuai Gao (School of Economics and Political Science, University of Sydney) |
| Abstract: | This paper introduces an easy to follow method for continuous time model estimation. It serves as an introduction on how to convert a state space model from continuous time to discrete time, how to decompose a hybrid stochastic model into a trend model plus a noise model, how to estimate the trend model by simulation, and how to calculate standard errors from estimation of the noise model. It also discusses the numerical difficulties involved in discrete time models that bring about the unit roots illusion in econometrics. |
| Keywords: | Continuous time model; Estimation; Trend and noise decomposition; Unit roots illusion |
| JEL: | C13 C22 C32 C51 |
| Date: | 2004–12–01 |
| URL: | http://d.repec.org/n?u=RePEc:uts:wpaper:138&r=ets |
| By: | Antonio E. Noriega (School of Economics, Universidad de Guanajuato); Daniel Ventosa-Santaularia (School of Economics, Universidad de Guanajuato) |
| Abstract: | We study the phenomenon of spurious regression between two random variables, when the generating mechanism of individual series is assumed to follow a stationary process around a trend with (possibly) multiple breaks in the level and slope of trend. We develop the relevant asymptotic theory and show that the phenomenon of spurious regression occurs independently of the structure assumed for the errors. In contrast to previous findings, the presence of a spurious relationship will be less severe when breaks are present in the generating mechanism of individual series. This is true whether the regression model includes a linear trend or not. Simulations confirm our asymptotic results, and reveal that in finite samples, the phenomenon of spurious regression is sensitive to the presence of a linear trend in the regression model, and to the relative location of breaks within the sample. |
| Keywords: | Stationarity, Structural breaks, Spurious regression |
| JEL: | C22 |
| URL: | http://d.repec.org/n?u=RePEc:gua:wpaper:em200501&r=ets |