|
on Forecasting |
| By: | Ashton de Silva; Rob J. Hyndman; Ralph D. Snyder |
| Abstract: | The vector innovation structural time series framework is proposed as a way of modelling a set of related time series. Like all multi-series approaches, the aim is to exploit potential inter-series dependencies to improve the fit and forecasts. A key feature of the framework is that the series are decomposed into common components such as trend and seasonal effects. Equations that describe the evolution of these components through time are used as the sole way of representing the inter-temporal dependencies. The approach is illustrated on a bivariate data set comprising Australian exchange rates of the UK pound and US dollar. Its forecasting capacity is compared to other common single- and multi-series approaches in an experiment using time series from a large macroeconomic database. |
| Keywords: | Vector innovation structural time series, state space model, multivariate time series, exponential smoothing, forecast comparison, vector autoregression. |
| JEL: | C32 C51 C53 |
| Date: | 2007–05 |
| URL: | http://d.repec.org/n?u=RePEc:msh:ebswps:2007-3&r=for |
| By: | Silvestro Di Sanzo (Department of Economics, University Of Alicante) |
| Abstract: | Recent studies have showed that it is troublesome, in practice, to distinguish between long memory and nonlinear processes. Therefore, it is of obvious interest to try to capture both features of long memory and non-linearity into a single time series model to be able to assess their relative importance. In this paper we put forward such a model, where we combine the features of long memory and Markov nonlinearity. A Markov Chain Monte Carlo algorithm is proposed to estimate the model and evaluate its forecasting performance using Bayesian predictive densities. The resulting forecasts are a significant improvement over those obtained by the linear long memory and Markov switching models. |
| Keywords: | Markov-Switching models, Bootstrap, Gibbs Sampling |
| JEL: | C11 C15 C22 |
| Date: | 2007 |
| URL: | http://d.repec.org/n?u=RePEc:ven:wpaper:03_07&r=for |
| By: | Ana Beatriz Galvão (Queen Mary, University of London) |
| Abstract: | This paper proposes a new regression model – a smooth transition mixed data sampling (STMIDAS) approach – that captures recurrent changes in the ability of a high frequency variable in predicting a low frequency variable. The STMIDAS regression is employed for testing changes in the ability of financial variables in forecasting US output growth. The estimation of the optimal weights for aggregating weekly data inside the quarter improves the measurement of the predictive ability of the yield curve slope for output growth. Allowing for changes in the impact of the short-rate and the stock returns in future growth is decisive for finding in-sample and out-of-sample evidence of their predictive ability at horizons longer than one year. |
| Keywords: | Smooth transition, MIDAS, Predictive ability, Asset prices, Output growth |
| JEL: | C22 C53 E44 |
| Date: | 2007–05 |
| URL: | http://d.repec.org/n?u=RePEc:qmw:qmwecw:wp595&r=for |
| By: | Kevin J. Lansing |
| Abstract: | This paper derives a general class of intrinsic rational bubble solutions in a standard Lucas-type asset pricing model. I show that the rational bubble component of the price-dividend ratio can evolve as a geometric random walk without drift. The volatility of bubble innovations depends exclusively on fundamentals. Starting from an arbitrarily small positive value, the rational bubble expands and contracts over time in an irregular, wholly endogenous fashion, always returning to the vicinity of the fundamental solution. I also examine a near-rational solution in which the representative agent does not construct separate forecasts for the fundamental and bubble components of the asset price. Rather, the agent constructs only a single forecast for the total asset price that is based on a geometric random walk without drift. The agent's forecast rule is parameterized to match the moments of observable data. In equilibrium, the actual law of motion for the price-dividend ratio is stationary, highly persistent, and nonlinear. The agent's forecast errors exhibit near-zero autocorrelation at all lags, making it difficult for the agent to detect a misspecification of the forecast rule. Unlike a rational bubble, the near-rational solution allows the asset price to occasionally dip below its fundamental value. Under mild risk aversion, the near-rational solution generates pronounced low-frequency swings in the price-dividend ratio, positive skewness, excess kurtosis, and time-varying volatility--all of which are present in long-run U.S. stock market data. An independent contribution of the paper is to demonstrate an approximate analytical solution for the fundamental asset price that employs a nonlinear change of variables. |
| Keywords: | Stock - Prices ; Forecasting |
| Date: | 2007 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedfwp:2007-10&r=for |
| By: | Taylor, Svetlana M. (Cardiff Business School) |
| Abstract: | This study investigates the association between the ownership structure of a firm and the accuracy of individual one-year-ahead earnings forecasts made by UK analysts. The relationship is explored in the presence of individual analyst and firm-specific characteristics using a research-tailored dataset comprising 11,659 individual analysts' forecasts made over the period, 1996 to 2001. To address the multidimensional variation in the dependent variables employed in the study (i.e., a forecast made by analyst i for firm j in year t) and the unique nature of the research question (i.e., the combined use of firm and analyst-specific characteristics), we use an analyst-firm fixed effects estimator. We are not aware of any UK studies in the field that investigate the role of ownership structure of a firm in determining the accuracy of analysts' forecasts. Furthermore, to the best of our knowledge, use of the analyst-firm fixed effect estimator in this context is also novel. The results of the study suggest that insider ownership is associated with forecast accuracy in a non-linear way. Moreover, although analysts are more optimistic for firms with a higher institutional ownership, institutional shareholders seem to be ineffective at addressing the agency disclosure problem. As a result, forecasts made for high institutional ownership firms are less accurate. |
| Keywords: | Analysts' forecasts; ownership structure |
| JEL: | G1 G3 |
| Date: | 2007–02 |
| URL: | http://d.repec.org/n?u=RePEc:cdf:accfin:2007/1&r=for |
| By: | Taylor, Svetlana M. (Cardiff Business School) |
| Abstract: | This paper examines the relationship between the board structure of UK firms and the accuracy of individual analysts' earnings forecasts with respect to information asymmetry and agency theory. We hypothesize that managers of firms complying with the recommendations of The Code of Best Practice may have "less to hide" and, subsequently, provide more information to outsiders (including analysts), thus facilitating more accurate analysts' forecasts. We find that analysts are more optimistic, but less accurate, for firms with a greater proportion of non-executive directors. This indicates that non-executive directors are inefficient at addressing the agency disclosure problem (at least in terms of the accuracy of analysts. earnings forecasts). |
| Keywords: | Financial analysts; Forecast accuracy; Corporate governance; Panel data |
| JEL: | G14 G29 G34 |
| Date: | 2007–03 |
| URL: | http://d.repec.org/n?u=RePEc:cdf:accfin:2007/2&r=for |
| By: | Frank Jotzo (Australian National University, Research School of Pacific and Asian Studies) |
| Abstract: | What is the magnitude of uncertainties about future greenhouse gas emissions, GDP and emissions intensity of economies? Is there a link between fluctuations in economic activity and fluctuations in emissions? These questions are crucial to understand the extent and composition of cost uncertainty under emissions trading schemes, the degree to which it can be reduced by mechanism design options such asintensity targets, and for calibrating models of emissions trading under uncertainty.This paper provides empirical analyses, using historical emissions data in forecast models and in country-level analysis over time. The results indicate that uncertainty about future energy sector CO2 emissions and emissions intensity is greater than uncertainty about future GDP; that uncertainties are greater in non-OECD than in OECD countries; and that there is a strong positive correlation between fluctuations in GDP and fluctuations in CO2 emissions, but not in all cases and not outside the energy sector. |
| Keywords: | Uncertainty; greenhouse gas emissions; GDP; emissions intensity; intensity targets; forecasting.; Uncertainty; greenhouse gas emissions; GDP; emissions intensity; intensity |
| JEL: | Q00 |
| Date: | 2006–07 |
| URL: | http://d.repec.org/n?u=RePEc:anu:eenwps:0603&r=for |
| By: | DeRossi, G.; Harvey, A. |
| Abstract: | A time-varying quantile can be fitted to a sequence of observations by formulating a time series model for the corresponding population quantile and iteratively applying a suitably modified state space signal extraction algorithm. It is shown that such time-varying quantiles satisfy the defining property of fixed quantiles in having the appropriate number of observations above and below. Expectiles are similar to quantiles except that they are defined by tail expectations. Like quantiles, time-varying expectiles can be estimated by a state space signal extraction algorithm and they satisfy properties that generalize the moment conditions associated with fixed expectiles. Time-varying quantiles and expectiles provide information on various aspects of a time series, such as dispersion and asymmetry, while estimates at the end of the series provide the basis for forecasting. Because the state space form can handle irregularly spaced observations, the proposed algorithms can be easily adapted to provide a viable means of computing spline-based non-parametric quantile and expectile regressions. |
| Keywords: | Asymmetric least squares; cubic splines; dispersion; non-parametric regression; quantile regression; signal extraction; state space smoother. |
| JEL: | C14 C22 |
| Date: | 2007–02 |
| URL: | http://d.repec.org/n?u=RePEc:cam:camdae:0660&r=for |
| By: | Uña, Gerardo; Bertello, Nicolas |
| Abstract: | After a period of positive fiscal results during years 2003 to 2005, the City of Buenos Aires faces challenges in its fiscal situation as of year 2006, which surely will be reflected in exercise 2007. During the period the 2003- 2005 City accumulated positive financial results near $1,800 million, starts off of which, $418 million, they were destined to the Stabilization Fund created in 2003 by Decree of the Executive authority. The estimations made by the Executive authority on the closing of exercise 2006 at the time of presenting the Project of Budget 2007 show a negative result of -$1,096 million, the contained negative result in Budget 2007 bases similar originally elevated by the Executive to the Legislature, and later modified in the parliamentary approval. As opposed to an electoral year, where the pressures on the public expenditure usually increase, it is precise to strengthening the institutionalization and transparency of the Buenos Aires City Stabilization Fund. |
| Keywords: | Fiscal Policy-Stabilization Fund-Budget Process-Legislature |
| JEL: | E62 H72 |
| Date: | 2007–03 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:3198&r=for |