|
on Forecasting |
| By: | Leonardo Morales-Arias (University of Kiel); Alexander Dross |
| Abstract: | This article investigates the statistical and economic implications of adaptive forecasting of exchange rates with panel data and alternative predictors. The candidate exchange rate predictors are drawn from (i) macroeconomic 'fundamentals', (ii) return/volatility of asset markets and (iii) cyclical and confidence indices. Exchange rate forecasts at various horizons are obtained from each of the potential predictors using single market, mean group and pooled estimates by means of rolling window and recursive forecasting schemes. The capabilities of single predictors and of adaptive techniques for combining the generated exchange rate forecasts are subsequently examined by means of statistical and economic performance measures. The forward premium and a predictor based on a Taylor rule yield the most promising forecasting results out of the macro 'fundamentals' considered. For recursive forecasting, confidence indices and volatility in-mean yield more accurate forecasts than most of the macro 'fundamentals'. Adaptive forecast combinations techniques improve forecasting precision and lead to better market timing than most single predictors at higher horizons. |
| Keywords: | exchange rate forecasting; panel data; forecast combinations; market timing |
| JEL: | C20 F31 G12 |
| Date: | 2010–10–01 |
| URL: | http://d.repec.org/n?u=RePEc:uts:rpaper:285&r=for |
| By: | Roxana Halbleib (European Center for Advanced Research in Economics and Statistics (ECARES), Université libre de Bruxelles, Solvay Brussels School of Economics and Management and CoFE); Valeri Voev (School of Economics and Management, Aarhus University and CREATES) |
| Abstract: | This paper proposes a new method for forecasting covariance matrices of financial returns. The model mixes volatility forecasts from a dynamic model of daily realized volatilities estimated with high-frequency data with correlation forecasts based on daily data. This new approach allows for flexible dependence patterns for volatilities and correlations, and can be applied to covariance matrices of large dimensions. The separate modeling of volatility and correlation forecasts considerably reduces the estimation and measurement error implied by the joint estimation and modeling of covariance matrix dynamics. Our empirical results show that the new mixing approach provides superior forecasts compared to multivariate volatility specifications using single sources of information. |
| Keywords: | Volatility forecasting, High-frequency data, Realized variance |
| JEL: | C32 C53 G11 |
| Date: | 2011–01–18 |
| URL: | http://d.repec.org/n?u=RePEc:aah:create:2011-03&r=for |
| By: | Roxana Halbleib; Valerie Voev |
| Abstract: | This paper analyzes the forecast accuracy of the multivariate realized volatility model introduced by Chiriac and Voev (2010), subject to different degrees of model parametrization and economic evaluation criteria. By modelling the Cholesky factors of the covariance matrices, the model generates positive definite, but biased covariance forecasts. In this paper, we provide empirical evidence that parsimonious versions of the model generate the best covariance forecasts in the absence of bias correction. Moreover, we show by means of stochastic dominance tests that any risk averse investor, regardless of the type of utility function or return distribution, would be better-off from using this model than from using some standard approaches. |
| Keywords: | Forecasting; Fractional integration; Stochastic dominance; Portfolio optimization; Realized covariance |
| JEL: | C32 C53 G11 |
| Date: | 2010–12 |
| URL: | http://d.repec.org/n?u=RePEc:eca:wpaper:2013/73585&r=for |
| By: | Xin Jin (Department of Economics, University of Toronto, Canada); John M. Maheu (Department of Economics, University of Toronto, Canada; The Rimini Centre for Economic Analysis (RCEA), Italy) |
| Abstract: | This paper proposes new dynamic component models of returns and realized covariance (RCOV) matrices based on time-varying Wishart distributions. Bayesian estimation and model comparison is conducted with a range of multivariate GARCH models and existing RCOV models from the literature. The main method of model comparison consists of a term-structure of density forecasts of returns for multiple forecast horizons. The new joint return-RCOV models provide superior density forecasts for returns from forecast horizons of 1 day to 3 months ahead as well as improved point forecasts for realized covariances. Global minimum variance portfolio selection is improved for forecast horizons up to 3 weeks out. |
| Keywords: | Wishart distribution, predictive likelihoods, density forecasts, MCMC |
| JEL: | C11 C32 C53 |
| Date: | 2011–01 |
| URL: | http://d.repec.org/n?u=RePEc:rim:rimwps:08_11&r=for |
| By: | Ardia, David; Lennart, Hoogerheide; Nienke, Corré |
| Abstract: | Using well-known GARCH models for density prediction of daily S&P 500 and Nikkei 225 index returns, a comparison is provided between frequentist and Bayesian estimation. No significant difference is found between the qualities of the forecasts of the whole density, whereas the Bayesian approach exhibits significantly better left-tail forecast accuracy. |
| Keywords: | GARCH; Bayesian; KLIC; censored likelihood |
| JEL: | C52 C22 C11 |
| Date: | 2011–01–17 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:28259&r=for |
| By: | Michael McAleer (Econometrisch Instituut (Econometric Institute), Faculteit der Economische Wetenschappen (Erasmus School of Economics) Erasmus Universiteit, Tinbergen Instituut (Tinbergen Institute).); Juan-Ángel Jiménez-Martín (Departamento de Economía Cuantitativa (Department of Quantitative Economics), Facultad de Ciencias Económicas y Empresariales (Faculty of Economics and Business), Universidad Complutense de Madrid); Teodosio Pérez-Amaral (Departamento de Economía Cuantitativa (Department of Quantitative Economics), Facultad de Ciencias Económicas y Empresariales (Faculty of Economics and Business), Universidad Complutense de Madrid) |
| Abstract: | A risk management strategy that is designed to be robust to the Global Financial Crisis (GFC), in the sense of selecting a Value-at-Risk (VaR) forecast that combines the forecasts of different VaR models, was proposed in McAleer et al. (2010c). The robust forecast is based on the median of the point VaR forecasts of a set of conditional volatility models. Such a risk management strategy is robust to the GFC in the sense that, while maintaining the same risk management strategy before, during and after a financial crisis, it will lead to comparatively low daily capital charges and violation penalties for the entire period. This paper presents evidence to support the claim that the median point forecast of VaR is generally GFC-robust. We investigate the performance of a variety of single and combined VaR forecasts in terms of daily capital requirements and violation penalties under the Basel II Accord, as well as other criteria. In the empirical analysis, we choose several major indexes, namely French CAC, German DAX, US Dow Jones, UK FTSE100, Hong Kong Hang Seng, Spanish Ibex35, Japanese Nikkei, Swiss SMI and US S&P500. The GARCH, EGARCH, GJR and Riskmetrics models, as well as several other strategies, are used in the comparison. Backtesting is performed on each of these indexes using the Basel II Accord regulations for 2008-10 to examine the performance of the Median strategy in terms of the number of violations and daily capital charges, among other criteria. The Median is shown to be a profitable and safe strategy for risk management, both in calm and turbulent periods, as it provides a reasonable number of violations and daily capital charges. The Median also performs well when both total losses and the asymmetric linear tick loss function are considered |
| Keywords: | Median strategy, Value-at-Risk (VaR), daily capital charges, robust forecasts, violation penalties, optimizing strategy, aggressive risk management, conservative risk management, Basel II Accord, global financial crisis (GFC). |
| JEL: | G32 G11 C53 C22 |
| Date: | 2011 |
| URL: | http://d.repec.org/n?u=RePEc:ucm:doicae:1101&r=for |
| By: | Ulrich K. Müller; James H. Stock |
| Abstract: | We propose a Bayesian procedure for exploiting small, possibly long-lag linear predictability in the innovations of a finite order autoregression. We model the innovations as having a log-spectral density that is a continuous mean-zero Gaussian process of order 1/√T. This local embedding makes the problem asymptotically a normal-normal Bayes problem, resulting in closed-form solutions for the best forecast. When applied to data on 132 U.S. monthly macroeconomic time series, the method is found to improve upon autoregressive forecasts by an amount consistent with the theoretical and Monte Carlo calculations. |
| JEL: | C11 C22 C32 |
| Date: | 2011–01 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:16714&r=for |
| By: | Bera, Soumitra Kumar |
| Abstract: | This study seeks to generate the forecasts for the small scale industrial sector of West Bengal for the ensuing decade till 2019-20. Forecasts have been generated for production, direct employment, capital formation and number of units in this sector. Auto Regressive Integrated Moving Average (ARIMA) model has been used taking the lead time of 13 years. The analysis of forecasted figures has revealed that the fixed capital investment and production would experience significant growth during the lead time of thirteen years. Number of units and employment are expected to observe meager growth during this period indicating low possibility of absorption of labor force in this sector. In the light of the forecasts, it is required on the part of the state government to take all concerted efforts and initiatives to strengthen the industrial base in West Bengal. In this regard catastrophic changes are required so far as industrial policy of West Bengal is concerned. |
| Keywords: | Stationarity; ARIMA models; Forecasts |
| JEL: | C13 C51 C22 |
| Date: | 2010–11–20 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:28144&r=for |
| By: | Junko Koeda (Faculty of Economics, University of Tokyo) |
| Abstract: | This note analyzes the yield-curve predictability for GDP growth by modifying the time-series property of the interest rate process in Ang, Piazzesi, and Wei (2006). When interest rates have a unit root and term spreads are stationary, the short rate's forecasting role changes, and the combined information from the short rate and term spread intuitively reveals the relationship between the shift of yield curves and GDP growth. |
| Date: | 2011–01 |
| URL: | http://d.repec.org/n?u=RePEc:tky:fseres:2011cf784&r=for |
| By: | Abbas , Qaiser; Rashid , Abdul |
| Abstract: | This paper aims to identify the financial ratios that are most significant in bankruptcy prediction for the non-financial sector of Pakistan based on a sample of companies which became bankrupt over the 1996-2006 period. Twenty four financial ratios covering four important financial attributes namely profitability, liquidity, leverage, and turnover ratios) were examined for a five-year period prior bankruptcy. The discriminant analysis produced a parsimonious model of three variables viz. sales to total assets, EBIT to current liabilities, and cash flow ratio. Our estimates provide evidence that the firms having Z value below zero fall into the “bankrupt” whereas the firms with Z value above zero fall into the “non-bankrupt” category. The model achieved 76.9% prediction accuracy when it is applied to forecast bankruptcies on the underlying sample. |
| Keywords: | Bankruptcy; Z-Score; Non-Financial Firms; Financial Ratios; Pakistan |
| JEL: | G33 |
| Date: | 2011–01–01 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:28161&r=for |
| By: | Graziani, Rebecca (Department of Decision Sciences, Bocconi University, Milano); Keilman, Nico (Dept. of Economics, University of Oslo) |
| Abstract: | The Scaled Model of Error has gained considerable popularity during the past ten years as a device for computing probabilistic population forecasts of the cohort-component type. In this report we investigate how sensitive probabilistic population forecasts produced by means of the Scaled Model of Error are for small changes in the correlation parameters. We consider changes in the correlation of the age-specific fertility forecast error increments across time and age, and changes in the correlation of the age-specific mortality forecast error increments across time, age and sex. Next we analyse the impact of such changes on the forecasts of the Total Fertility Rate and of the Male and Female Life Expectancies respectively. For age specific fertility we find that the correlation across ages has only limited impact on the uncertainty in the Total Fertility Rate. As a consequence, annual numbers of births will be little affected. The autocorrelation in error increments is an important parameter, in particular in the long run. Also, the autocorrelation in error increments for age specific mortality is important. It has a large effect on long run uncertainty in life expectancy values, and hence on the uncertainty around the elderly population in the future. In empirical applications of the Scaled Model of Error, one should give due attention to a correct estimation of these two parameters. |
| Keywords: | Scaled model of error; Stochastic population forecast; Probabilistic cohort component model; Sensitivity; Correlation |
| JEL: | C15 C49 C63 J40 |
| Date: | 2010–11–23 |
| URL: | http://d.repec.org/n?u=RePEc:hhs:osloec:2010_022&r=for |