|
on Econometric Time Series |
| By: | Robinson Kruse (Aarhus University and CREATES); Michael Frömmel (Ghent University); Lukas Menkhoff (Leibniz University Hannover); Philipp Sibbertsen (Leibniz University Hannover) |
| Abstract: | This research points to the serious problem of potentially misspecified alternative hypotheses when testing for unit roots in real exchange rates. We apply a popular unit root test against nonlinear ESTAR and develop a Markov Switching unit root test. The empirical power of these tests against correctly and misspecified non-linear alternatives is analyzed by means of a Monte Carlo study. The chosen parametrization is obtained by real-life exchange rates. The test against ESTAR has low power against all alternatives whereas the proposed unit root test against a Markov Switching autoregressive model performs clearly better. An empirical application of these tests suggests that real exchange rates may indeed be explained by Markov-Switching dynamics. |
| Keywords: | real exchange rates, unit root test, ESTAR, Markov Switching, PPP |
| JEL: | C12 C22 F31 |
| Date: | 2009–05–28 |
| URL: | http://d.repec.org/n?u=RePEc:aah:create:2009-50&r=ets |
| By: | Isabel Casas (Aarhus University and CREATES); Irene Gijbels (Katholieke Universiteit Leuven) |
| Abstract: | The objective of this paper is to introduce the break preserving local linear (BPLL) estimator for the estimation of unstable volatility functions. Breaks in the structure of the conditional mean and/or the volatility functions are common in Finance. Markov switching models (Hamilton, 1989) and threshold models (Lin and Terasvirta, 1994) are amongst the most popular models to describe the behaviour of data with structural breaks. The local linear (LL) estimator is not consistent at points where the volatility function has a break and it may even report negative values for finite samples. The estimator presented in this paper generalises the classical LL. The BPLL maintains the desirable properties of the LL with regard to the bias and the boundary estimation, it estimates the breaks consistently and it ensures that the volatility estimates are always positive. |
| Keywords: | Breaks estimation, Heteroscedasticity, Local linear regression, Nonlinear time series, Volatility estimation |
| JEL: | C13 C14 C22 |
| Date: | 2009–10–22 |
| URL: | http://d.repec.org/n?u=RePEc:aah:create:2009-48&r=ets |
| By: | Tue Gørgens (The Australian National University); Christopher L. Skeels (The University of Melbourne); Allan H. Würtz (School of Economics and Management, University of Aarhus and CREATES) |
| Abstract: | This paper explores estimation of a class of non-linear dynamic panel data models with additive unobserved individual-specific effects. The models are specified by moment restrictions. The class includes the panel data AR(p) model and panel smooth transition models. We derive an efficient set of moment restrictions for estimation and apply the results to estimation of panel smooth transition models with fixed effects, where the transition may be determined endogenously. The performance of the GMM estimator, both in terms of estimation precision and forecasting performance, is examined in a Monte Carlo experiment. We find that estimation of the parameters in the transition function can be problematic but that there may be significant benefits in terms of forecast performance. |
| Keywords: | Dynamic panel data models, fixed effects, GMM estimation, smooth transition |
| JEL: | C13 C23 |
| Date: | 2009–10–01 |
| URL: | http://d.repec.org/n?u=RePEc:aah:create:2009-51&r=ets |
| By: | Kajal Lahiri; Xuguang Sheng |
| Abstract: | Using a standard decomposition of forecasts errors into common and idiosyncratic shocks, we show that aggregate forecast uncertainty can be expressed as the disagreement among the forecasters plus the perceived variability of future aggregate shocks. Thus, the reliability of disagreement as a proxy for uncertainty will be determined by the stability of the forecasting environment, and the length of the forecast horizon. Using density forecasts from the Survey of Professional Forecasters, we find direct evidence in support of our hypothesis. Our results support the use of GARCH-type models, rather than the ex post squared errors in consensus forecasts, to estimate the ex ante variability of aggregate shocks as a component of aggregate uncertainty. |
| Date: | 2009 |
| URL: | http://d.repec.org/n?u=RePEc:nya:albaec:09-06&r=ets |
| By: | George Monokroussos |
| Abstract: | Estimating Limited Dependent Variable Time Series models through standard extremum methods can be a daunting computational task because of the need for integration of high order multiple integrals and/or numerical optimization of difficult objective functions. This paper proposes a classical Markov Chain Monte Carlo (MCMC) estimation technique with data augmentation that overcomes both of these problems. The asymptotic properties of the proposed estimator are established. Furthermore, a practical and flexible algorithmic framework for this class of models is proposed and is illustrated using simulated data, thus also offering some insight into the small-sample biases of such estimators. Finally, the versatility of the proposed framework is illustrated with an application of a dynamic tobit model for the Open Market Desk's Daily Reaction Function. |
| Date: | 2009 |
| URL: | http://d.repec.org/n?u=RePEc:nya:albaec:09-07&r=ets |
| By: | Kajal Lahiri; Fushang Liu |
| Abstract: | Abstract: We consider how to use information from reported density forecasts from surveys to identify asymmetry in forecasters' loss functions. We show that, for the three common loss functions - Lin-Lin, Linex, and Quad-Quad - we can infer the direction of loss asymmetry by just comparing point forecasts and the central tendency (mean or median) of the underlying density forecasts. If we know the entire distribution of the density forecast, we can calculate the loss function parameters based on the first order condition of forecast optimality. This method is applied to forecasts for annual real output growth and inflation obtained from the Survey of Professional Forecasters (SPF). We find that forecasters treat underprediction of real output growth more dearly than overprediction, reverse is true for inflation. |
| Date: | 2009 |
| URL: | http://d.repec.org/n?u=RePEc:nya:albaec:09-03&r=ets |
| By: | James W. Taylor; Ralph D. Snyder |
| Abstract: | This paper concerns the forecasting of seasonal intraday time series. An extension of Holt-Winters exponential smoothing has been proposed that smoothes an intraday cycle and an intraweek cycle. A recently proposed exponential smoothing method involves smoothing a different intraday cycle for each distinct type of day of the week. Similar days are allocated identical intraday cycles. A limitation is that the method allows only whole days to be treated as identical. We introduce an exponential smoothing formulation that allows parts of different days of the week to be treated as identical. The result is a method that involves the smoothing and initialisation of fewer terms than the other two exponential smoothing methods. We evaluate forecasting up to a day ahead using two empirical studies. For electricity load data, the new method compares well with a range of alternatives. The second study involves a series of arrivals at a call centre that is open for a shorter duration at the weekends than on weekdays. By contrast with the previously proposed exponential smoothing methods, our new method can model in a straightforward way this situation, where the number of periods on each day of the week is not the same. |
| Keywords: | Exponential smoothing; Intraday data; Electricity load; Call centre arrivals. |
| JEL: | C22 |
| Date: | 2009–10–02 |
| URL: | http://d.repec.org/n?u=RePEc:msh:ebswps:2009-9&r=ets |
| By: | Herwartz , Helmut; Siedenburg, Florian |
| Abstract: | Noting that many economic variables display occasional shifts in their second order moments, we investigate the performance of homogenous panel unit root tests in the presence of permanent volatility shifts. It is shown that in this case, panel unit root tests derived under time invariant innovation variances lose control over actual significance levels while the test proposed by Herwartz and Siedenburg (2008) retains size control. A simulation study of the finite sample properties confirms the theoretical results in finite samples. As an empirical illustration, we reassess evidence on the Fisher hypothesis. |
| Keywords: | Panel unit root tests,variance breaks,cross sectional dependence,Fisher hypothesis |
| JEL: | C23 C12 E40 |
| Date: | 2009 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:cauewp:200907&r=ets |
| By: | Herwartz , Helmut; Siedenburg, Florian |
| Abstract: | A novel simulation based approach to unit root testing is proposed in this paper. The test is constructed from the distinct orders in probability of the OLS parameter estimates obtained from a spurious and an unbalanced regression, respectively. While the parameter estimate from a regression of two integrated and uncorrelated time series is of order Op(1), the estimate is of order Op(T-1) if the dependent variable is stationary. The test statistic is constructed as an inter quantile range from the empirical distribution obtained from regressing the standardized data sufficiently often on controlled random walks. GLS detrending (Elliott et al, 1996) and spectral density variance estimators (Perron and Ng, 1998) are applied to account for deterministic terms and residual autocorrelation in the data. A Monte Carlo study confirms that the proposed test has favorable empirical size properties and is powerful in local-to-unity neighborhoods. Testing for PPP for a sample of G6 economies, the proposed test yields results in favor of PPP for half of the sample economies while benchmark tests obtain at most one rejection of the random walk null hypothesis. |
| Keywords: | Unit root tests,simulation based test,simulation study,GLS detrending |
| JEL: | C22 C12 |
| Date: | 2009 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:cauewp:200906&r=ets |
| By: | Knüppel, Malte |
| Abstract: | Multi-step-ahead forecasts of forecast uncertainty in practice are often based on the horizon-specific sample means of recent squared forecast errors, where the number of available past forecast errors decreases one-to-one with the forecast horizon. In this paper, the efficiency gains from the joint estimation of forecast uncertainty for all horizons in such samples are investigated. Considering optimal forecasts, the efficiency gains can be substantial if the sample is not too large. If forecast uncertainty is estimated by seemingly unrelated regressions, the covariance matrix of the squared forecast errors does not have to be estimated, but simply needs to have a certain structure. In Monte Carlo studies it is found that seemingly unrelated regressions mostly yield estimates which are more efficient than the sample means even if the forecasts are not optimal. Seemingly unrelated regressions are used to address questions concerning the inflation forecast uncertainty of the Bank of England. |
| Keywords: | Multi-step-ahead forecasts,forecast error variance,GLS,SUR |
| JEL: | C13 C32 C53 |
| Date: | 2009 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp1:200928&r=ets |