|
on Forecasting |
| By: | Alysha M De Livera; Rob J Hyndman |
| Abstract: | A new innovations state space modeling framework, incorporating Box-Cox transformations, Fourier series with time varying coefficients and ARMA error correction, is introduced for forecasting complex seasonal time series that cannot be handled using existing forecasting models. Such complex time series include time series with multiple seasonal periods, high frequency seasonality, non-integer seasonality and dual-calendar effects. Our new modelling framework provides an alternative to existing exponential smoothing models, and is shown to have many advantages. The methods for initialization and estimation, including likelihood evaluation, are presented, and analytical expressions for point forecasts and interval predictions under the assumption of Gaussian errors are derived, leading to a simple, comprehensible approach to forecasting complex seasonal time series. Our trigonometric formulation is also presented as a means of decomposing complex seasonal time series, which cannot be decomposed using any of the existing decomposition methods. The approach is useful in a broad range of applications, and we illustrate its versatility in three empirical studies where it demonstrates excellent forecasting performance over a range of prediction horizons. In addition, we show that our trigonometric decomposition leads to the identification and extraction of seasonal components, which are otherwise not apparent in the time series plot itself. |
| Keywords: | Exponential smoothing, Fourier series, prediction intervals, seasonality, state space models, time series decomposition |
| JEL: | C22 C53 |
| Date: | 2009–12–12 |
| URL: | http://d.repec.org/n?u=RePEc:msh:ebswps:2009-15&r=for |
| By: | Anna Staszewska-Bystrova |
| Abstract: | The problem of forecasting from vector autoregressive models has attracted considerable attention in the literature. The most popular non-Bayesian approaches use large sample normal theory or the bootstrap to evaluate the uncertainty associated with the forecast. The literature has concentrated on the problem of assessing the uncertainty of the prediction for a single period. This paper considers the problem of how to assess the uncertainty when the forecasts are done for a succession of periods. It describes and evaluates bootstrap method for constructing confidence bands for forecast paths. The bands are constructed from forecast paths obtained in bootstrap replications with an optimisation procedure used to find the envelope of the most concentrated paths. The method is shown to have good coverage properties in a Monte Carlo study. |
| Keywords: | vector autoregression, forecast path, bootstrapping, simultaneous statistical inference |
| JEL: | C15 C32 C53 |
| Date: | 2009–12–07 |
| URL: | http://d.repec.org/n?u=RePEc:com:wpaper:024&r=for |
| By: | Morley, Bruce |
| Abstract: | Using the ARDL bounds testing approach to cointegration this paper provides evidence of a stable long run relationship between the exchange rate and stock prices for the UK, Japan and Swiss currencies with respect to the US dollar. The resultant error correction models suggest a positive relationship between stock prices and the exchange rate, which in an out-of-sample forecast outperforms the random walk. We compare these results with a similar model incorporating interest rates, suggested by Solnik (1987), however this does not in general improve the results. |
| Keywords: | Exchange Rates; Stock Prices; Forecast; Cointegration |
| Date: | 2009 |
| URL: | http://d.repec.org/n?u=RePEc:eid:wpaper:5/09&r=for |
| By: | Jean-Baptiste Dherbecourt; Bastien Drut |
| Abstract: | Contributing to the lively debate on closed leagues (North American model) versus open leagues (European model) in professional sport league, this paper aims at determining the drivers of promotion and relegation in the major European soccer leagues. Using a large and original dataset (for example: club’s link with a billionaire, club listed in the stock market, etc.) and logistic regressions, our results show that institutional factors matter to settle in the elite. It also indicates that open leagues system in European soccer championships is de facto very similar to closed leagues system. Furthermore, our forecasting model can be of interest for soccer investors or bookmakers. |
| Keywords: | Economics of Sport, Organization of Sports Leagues, Soccer, Promotion and Relegation, Economic Forecasting, Regional Economy, Billionaires, Stock Market. |
| JEL: | L83 R11 R58 |
| Date: | 2009 |
| URL: | http://d.repec.org/n?u=RePEc:drm:wpaper:2009-40&r=for |
| By: | Dmitry Kucharavy (LGeco - Laboratoire de Génie de la Conception - Institut National des Sciences Appliquées de Strasbourg); Eric Schenk (LGeco - Laboratoire de Génie de la Conception - Institut National des Sciences Appliquées de Strasbourg); Roland De Guio (LGeco - Laboratoire de Génie de la Conception - Institut National des Sciences Appliquées de Strasbourg) |
| Abstract: | In this paper applications of logistic S-curve and component logistics are considered in a framework of long-term forecasting of emerging technologies. Several questions and issues are discussed in connection with the presented ways of studying the transition from invention to innovation and further evolution of technologies. First, the features of a simple logistic model are presented and diverse types of competition are discussed. Second, a component logistic model is presented. Third, a hypothesis about the usability of a knowledge growth description and simulation for reliable long-term forecasting is proposed. Some interim empirical results for applying networks of contradictions are given. |
| Keywords: | component logistic model, innovation process, knowledge acquisition, OTSM-TRIZ |
| Date: | 2009–03 |
| URL: | http://d.repec.org/n?u=RePEc:hal:wpaper:halshs-00440438_v1&r=for |
| By: | Ferdinand Fichtner (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.); Rasmus Rüffer (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.); Bernd Schnatz (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.) |
| Abstract: | Using OECD composite leading indicators (CLI), we assess empirically whether the ability of the country-specific CLIs to predict economic activity has diminished in recent years, e.g. due to rapid advances in globalisation. Overall, we find evidence that the CLI encompasses useful information for forecasting industrial production, particularly over horizons of four to eight months ahead. The evidence is particularly strong when taking cointegration relationships into account. At the same time, we find indications that the forecast accuracy has declined over time for several countries. Augmenting the country-specific CLI with a leading indicator of the external environment and employing forecast combination techniques improves the forecast performance for several economies. Over time, the increasing importance of international dependencies is documented by relative performance gains of the extended model for selected countries. JEL Classification: C53, E32, E37, F47. |
| Keywords: | Leading Indicator, Business Cycle, Forecast Comparison, Globalisation, Structural Change. |
| Date: | 2009–12 |
| URL: | http://d.repec.org/n?u=RePEc:ecb:ecbwps:20091125&r=for |