|
on Forecasting |
| By: | Schumacher, Christian |
| Abstract: | This paper discusses the forecasting performance of alternative factor models based on a large panel of quarterly time series for the german economy. One model extracts factors by static principals components analysis, the other is based on dynamic principal components obtained using frequency domain methods. The third model is based on subspace algorithm for state space models. Out-of-sample forecasts show that the prediction errors of the factor models are generally smaller than the errors of simple autoregressive benchmark models. Among the factors models, either the dynamic principal component model or the subspace factor model rank highest in terms of forecast accuracy in most cases. However, neither of the dynamic factor models can provide better forecasts than the static model over all forecast horizons and different specifications of the simulation design. Therefore, the application of the dynamic factor models seems to provide only small forecasting improvements over the static factor model for forecasting German GDP. |
| Keywords: | Factor models, static and dynamic factors, principal components, forecasting accuracy |
| JEL: | C43 C51 E32 |
| Date: | 2005 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp1:4218&r=for |
| By: | Isabel Yi Zheng; James Rossiter |
| Abstract: | The authors build a model for predicting current-quarter real gross domestic product (GDP) growth using anywhere from zero to three months of indicators from that quarter. Their equation links quarterly Canadian GDP growth with monthly data on retail sales, housing starts, consumer confidence, total hours worked, and U.S. industrial production. The authors use time-series methods to forecast missing observations of the monthy indicators; this allows them to assess the performance of the method under various amounts of monthly information. The authors' model forecasts GDP growth as early as the first month of the reference quarter, and its accuracy generally improves with incremental monthly data releases. The final forecast from the model, available five to six weeks before the release of the National Income and Expenditure Accounts, delivers improved accuracy relative to those of several macroeconomic models used for short-term forecasting of Canadian output. The implications of real-time versus pseudo-real-time forecasting are investigated, and the authors find that the choice between real-time and latestavailable data affects the performance ranking among alternative models. |
| Keywords: | Economic models; Econometric and statistical methods |
| JEL: | C22 C53 |
| Date: | 2006 |
| URL: | http://d.repec.org/n?u=RePEc:bca:bocawp:06-26&r=for |
| By: | Robert Rich; Joseph Tracy |
| Abstract: | This paper examines matched point and density forecasts of inflation from the Survey of Professional Forecasters to analyze the relationship between expected inflation, disagreement, and uncertainty. We extend previous studies through our data construction and estimation methodology. Specifically, we derive measures of disagreement and uncertainty by using a decomposition proposed in earlier research by Wallis and by applying the concept of entropy from information theory. We also undertake the empirical analysis within a seemingly unrelated regression framework. Our results offer mixed support for the propositions that disagreement is a useful proxy for uncertainty and that increases in expected inflation are accompanied by heightened inflation uncertainty. However, we document a robust, quantitatively and statistically significant positive association between disagreement and expected inflation. |
| Keywords: | Inflation (Finance) ; Economic forecasting ; Information theory ; Uncertainty |
| Date: | 2006 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fednsr:253&r=for |
| By: | Eric Parrado; Turgut Kisinbay; Rodolfo Maino; Jorge Iván Canales Kriljenko |
| Abstract: | How should a central bank organize itself to produce the best possible inflation forecast? This paper discusses elements for building a comprehensive platform for an inflation forecasting framework. It describes the exercise of forecasting inflation as a production process, which induces a strict discipline concerning data management, information gathering, the use of a suitable statistical apparatus, and the exercise of sound communication strategies to reinforce reputation and credibility. It becomes critical how a central bank organizes itself to produce relevant macroeconomic forecasts, with special consideration to product design, the essential requirements needed in the forecasting process, and key related organizational issues. In addition, the paper proposes to factor into the process the authorities' policy responses to previous inflation forecasts in order to be consistent with the spirit of the inflation targeting framework. |
| Keywords: | Inflation , Central bank organization , Inflation targeting , Monetary policy , Central bank policy , Data collection , Data analysis , Forecasting models , |
| Date: | 2006–05–19 |
| URL: | http://d.repec.org/n?u=RePEc:imf:imfwpa:06/122&r=for |
| By: | Greg Tkacz; Carolyn Wilkins |
| Abstract: | The authors examine whether simple measures of Canadian equity and housing price misalignments contain leading information about output growth and inflation. Previous authors have found that the information content of asset prices in general, and equity and housing prices in particular, are unreliable in that they do not systematically predict future economic activity or inflation. However, earlier studies relied on simple linear relationships that would fail to pick up the potential non-linear effects of asset-price misalignments. The authors' results suggest that housing prices are useful for predicting GDP growth, even within a linear context. Moreover, both stock and housing prices can improve inflation forecasts, especially when using a threshold specification. These improvements in forecast performance are relative to the information contained in Phillips-curve type indicators for inflation and IS-curve type indicators for GDP growth. |
| Keywords: | Inflation and prices; Business fluctuations and cycles |
| JEL: | C53 E4 |
| Date: | 2006 |
| URL: | http://d.repec.org/n?u=RePEc:bca:bocawp:06-25&r=for |
| By: | Döpke, Jörg; Hartmann, Daniel; Pierdzioch, Christian |
| Abstract: | We compared forecasts of stock market volatility based on real-time and revised macroeconomic data. To this end, we used a new dataset on monthly real-time macroeconomic variables for Germany. The dataset covers the period 1994-2005. We used a statistical, a utility-based, and an options-based criterion to evaluate volatility forecasts. Our main result is that the statistical and economic value of volatility forecasts based on real-time data is comparable to the value of forecasts based on revised macroeconomic data. |
| Keywords: | Forecasting stock market volatility, Real-time macroeconomic data, Evaluation of forecasting accuracy |
| JEL: | C53 E44 G11 |
| Date: | 2005 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp2:4357&r=for |
| By: | Carlo Altavilla; Paul De Grauwe |
| Abstract: | This paper investigates the out-of-sample forecast performance of a set of competing models of exchange rate determination. We compare standard linear models with models that characterize the relationship between exchange rate and its underlying fundamentals by nonlinear dynamics. Linear models tend to outperform at short forecast horizons especially when deviations from long-term equilibrium are small. In contrast, nonlinear models with more elaborate mean-reverting components dominate at longer horizons especially when deviations from long-term equilibrium are large. The results also suggest that combining different forecasting procedures generally produces more accurate forecasts than can be attained from a single model. |
| Keywords: | non-linearity, exchange rate modelling, forecasting |
| JEL: | C53 F31 |
| Date: | 2006 |
| URL: | http://d.repec.org/n?u=RePEc:ces:ceswps:_1747&r=for |
| By: | Craig, Ben; Keller, Joachim |
| Abstract: | We estimate the process underlying the pricing of American options by using higher-order lattices combined with a multigrid method. This paper also tests whether the risk-neutral densities given from American options provide a good forecasting tool. We use a nonparametric test of the densities that is based on the inverse probability functions and is modified to account for correlation across time between our random variables, which are uniform under the null hypothesis. We find that the densities based on the Americanoption markets for foreign exchange do quite well for the forecasting period over which the options are thickly traded. Further, simple models that fit the densities do about as well as more sophisticated models. Keywords: Risk-neutral densities from option prices, American exchange rate options, Evaluating Density Forecasts, Pentionominal tree, Density evaluation, Overlapping data problem |
| Keywords: | Risk-neutral densities from option prices, American exchange rate options, Evaluating Density Forecasts, Pentionominal tree, Density evaluation |
| JEL: | C52 C63 F31 F47 |
| Date: | 2005 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp2:4260&r=for |
| By: | Antonio Diez de los Rios |
| Abstract: | The author proposes an arbitrage-free model of the joint behaviour of interest and exchange rates whose exchange rate forecasts outperform those produced by a random-walk model, a vector autoregression on the forward premiums and the rate of depreciation, and the standard forward premium regression. In addition, the model is able to reproduce the forward premium puzzle. |
| Keywords: | Exchange rates; Interest rates; Econometric and statistical methods |
| JEL: | E43 F31 G12 G15 |
| Date: | 2006 |
| URL: | http://d.repec.org/n?u=RePEc:bca:bocawp:06-27&r=for |
| By: | Blaskowitz, Oliver; Herwartz, Helmut; de Cadenas Santiago, Gonzalo |
| Abstract: | In this study we forecast the term structure of FIBOR/EURIBOR swap rates by means of recursive vector autoregressive (VAR) models. In advance, a principal components analysis (PCA) is adopted to reduce the dimensionality of the term structure. To evaluate ex–ante forecasting performance for particular short, medium and long term rates and for the level, slope and curvature of the swap term structure, we rely on measures of both statistical and economic performance. Whereas the statistical performance is investigated by means of the Henrikkson–Merton statistic, the economic performance is assessed in terms of cash flows implied by alternative trading strategies. Arguing in favor of local homogeneity of term structure dynamics, we propose a data driven, adaptive model selection strategy to “predict the best forecasting model” out of a set of 100 alternative implementations of the PCA/VAR model. This approach is shown to outperform forecasting schemes relying on global homogeneity of the term structure. |
| Keywords: | Principal components, Factor Analysis, Ex–ante forecasting, EURIBOR swap rates, Term structure, Trading strategies |
| JEL: | C32 C53 E43 G29 |
| Date: | 2005 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:cauewp:2987&r=for |
| By: | Knetsch, Thomas A. |
| Abstract: | The paper develops an oil price forecasting technique which is based on the present value model of rational commodity pricing. The approach suggests shifting the forecasting problem to the marginal convenience yield which can be derived from the cost-of-carry relationship. In a recursive out-of-sample analysis, forecast accuracy at horizons within one year is checked by the root mean squared error as well as the mean error and the frequency of a correct direction-of-change prediction. For all criteria employed, the proposed forecasting tool outperforms the approach of using futures prices as direct predictors of future spot prices. Vis-à-vis the random-walk model, it does not significantly improve forecast accuracy but provides valuable statements on the direction of change. |
| Keywords: | oil price forecasts, rational commodity pricing, convenience yield, single-equation model |
| JEL: | C22 E37 G12 G13 Q40 |
| Date: | 2006 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp1:4353&r=for |
| By: | Khoon Lek Goh; Daniel Lawrence (The Treasury) |
| Abstract: | Work on assessing Treasury’s forecasting performance to date has focussed on comparisons against consensus forecasts. This study compares Treasury’s GDP and CPI forecast performance against individual private sector forecasters as well as major public sector institutions such as the IMF, OECD and the Reserve Bank of New Zealand. The head-to-head comparison makes it possible to assess Treasury’s forecasting performance relative to its peers. When compared across all evaluation periods covering 1996-2005, Treasury’s GDP forecast performance was ranked in the middle at seventh out of 16. The large forecast error for the 1998 year had a material impact on Treasury’s overall forecast performance. Treasury’s CPI forecast performance was not as good, placing tenth out of 12. Large forecast errors for the 1998-2000 period accounted for the poor CPI forecast performance. Treasury’s overall forecast performance was better when evaluating only the current year Budget forecasts, placing fourth for GDP and sixth for CPI. This suggests that Treasury is better at forecasting the current year than the year ahead. Consistent with international studies, no single forecaster consistently outperforms the Consensus, with Treasury beating the Mean 30% of the time for GDP and Consensus 33% of the time for CPI. All forecasters find it difficult to pick recessions and turning points. Large forecasting groups generally have a poorer forecasting record on average. |
| Keywords: | Forecast accuracy; New Zealand |
| JEL: | E27 E37 |
| Date: | 2006–07 |
| URL: | http://d.repec.org/n?u=RePEc:nzt:nztwps:06/10&r=for |
| By: | Philippe D Karam; Douglas Laxton; Andrew Berg |
| Abstract: | This paper provides a how-to guide to model-based forecasting and monetary policy analysis. It describes a simple structural model, along the lines of those in use in a number of central banks. This workhorse model consists of an aggregate demand (or IS) curve, a price-setting (or Phillips) curve, a version of the uncovered interest parity condition, and a monetary policy reaction function. The paper discusses how to parameterize the model and use it for forecasting and policy analysis, illustrating with an application to Canada. It also introduces a set of useful software tools for conducting a model-consistent forecast. |
| Keywords: | Monetary policy , Canada , United States , Monetary aggregates , Forecasting models , Economic models , |
| Date: | 2006–04–10 |
| URL: | http://d.repec.org/n?u=RePEc:imf:imfwpa:06/81&r=for |
| By: | Philippe D Karam; Douglas Laxton; Andrew Berg |
| Abstract: | This paper motivates and describes an approach to forecasting and monetary policy analysis based on the use of a simple structural macroeconomic model, along the lines of those in use in a number of central banks. It contrasts this approach with financial programming and its emphasis on monetary aggregates, as well as with more econometrically driven analyses. It presents illustrative results from an application to Canada. A companion paper provides a more detailed how-to guide and introduces a set of tools designed to facilitate this approach. |
| Keywords: | Monetary policy , Canada , United States , Monetary aggregates , Forecasting models , Economic models , |
| Date: | 2006–04–10 |
| URL: | http://d.repec.org/n?u=RePEc:imf:imfwpa:06/80&r=for |
| By: | Hofmann, Boris |
| Abstract: | This paper assesses the performance of monetary indicators in predicting euro area HICP inflation out-of-sample over the period since the start of EMU considering a wide range of forecasting models, including standard bivariate forecasting models, factor models, simple combination forecasts as well as trivariate two-pillar Phillips Curve type forecasting models. The results suggest that monetary indicators are still useful indicators for inflation in the euro area, but that a thorough and broad based monetary analysis is needed to extract the information content of monetary developments for future inflation. |
| Keywords: | euro area, inflation, leading indicators, money |
| JEL: | C32 E31 E40 |
| Date: | 2006 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp1:4469&r=for |
| By: | Allan Timmermann |
| Abstract: | The World Economic Outlook (WEO) is a key source of forecasts of global economic conditions. It is therefore important to review the performance of these forecasts against both actual outcomes and alternative forecasts. This paper conducts a series of statistical tests to evaluate the quality of the WEO forecasts for a very large cross section of countries, with particular emphasis on the recent recession and recovery. It assesses whether forecasts were unbiased and informationally efficient, and characterizes the process whereby WEO forecasts get revised as the time to the point of the forecast draws closer. Finally, the paper assess whether forecasts can be improved by combining WEO forecasts with the Consensus forecasts. The results suggest that the performance of the WEO forecasts is similar to that of the Consensus forecasts. While WEO forecasts for many variables in many countries meet basic quality standards in some, if not all, dimensions, the paper raises a number of concerns with current forecasting performance. |
| Keywords: | World Economic Outlook , Economic forecasting , Economic conditions , |
| Date: | 2006–03–15 |
| URL: | http://d.repec.org/n?u=RePEc:imf:imfwpa:06/59&r=for |
| By: | Breitung, Jörg; Eickmeier, Sandra |
| Abstract: | Factor models can cope with many variables without running into scarce degrees of freedom problems often faced in a regression-based analysis. In this article we review recent work on dynamic factor models that have become popular in macroeconomic policy analysis and forecasting. By means of an empirical application we demonstrate that these models turn out to be useful in investigating macroeconomic problems. |
| Keywords: | Principal components, dynamic factors, forecasting |
| JEL: | C13 C33 C51 |
| Date: | 2005 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp1:4232&r=for |
| By: | Fiorino, Nadia; Ricciuti, Roberto |
| Abstract: | We analyze the effect of different legislature size on per capita regional expenditure in Italy. According to the theory, legislature size has an indefinite effect on government spending because logrolling and transaction costs may have canceling effects. We find a large and significantly positive effect of the number of legislators. We use these findings to forecast the effects of the increase in the number of legislators that is taking place in some regions: a 10% increase in legislature size commands on average a 12% increase in per capita regional expenditure. |
| Keywords: | Legislature size, regional expenditure |
| JEL: | H72 H73 |
| Date: | 2006–07 |
| URL: | http://d.repec.org/n?u=RePEc:uca:ucapdv:69&r=for |
| By: | Tillmann, Peter |
| Abstract: | The canonical New Keynesian model specifies inflation as the present-value of future real marginal cost. This paper tests this New Keynesian Phillips Curve and exploits projections of future real marginal cost generated by VAR models to assess the model’s ability to match the behavior of actual inflation. In accordance to the literature, the model fits Euro data well at first sight. However, analyses of this kind disregard the considerable degree of uncertainty surrounding VAR forecasts. A set of bias-corrected bootstrapped confidence bands reveals that this result is consistent with both a well fitting and a completely failing model. Allowing for inflation inertia through backward-looking indexation narrows confidence bands around measures of the model’s fit but, still, cannot generate sufficiently precise estimates. Hence, we cannot say whether the model fits or fails. |
| Keywords: | New Keynesian Phillips Curve, present-value model, marginal cost, VAR, bootstrap |
| JEL: | E31 E32 |
| Date: | 2005 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp1:2938&r=for |
| By: | Stamfort, Stefan |
| Abstract: | This paper discusses various approaches to decompose economic time series into their trend and cyclical components. For over 30 years now, the Deutsche Bundesbank publishes trend-adjusted indicators in its Statistical Supplement 4 entitled “Seasonally Adjusted Business Statistics” which are calculated basically as unweighted moving averages. As alternatives to the Bundesbank’s current approach, the widely used Hodrick-Prescott filter, the extended exponential smoothing filter and the Baxter-King low-pass filter are investigated. All three of the filters are able to clearly separate the trend component from the cyclical component for German economic indicators. The turning points of the growth cycles are largely consistent with the Bundesbank’s current approach. However, the trend deviation level at the end of the series is still subject to noticeable changes. This uncertainty can be quantified with the help of ARIMA forecasts. The choice of filter ultimately depends on the features of the time series to be filtered. Whereas extended exponential smoothing is well suited to I(1) processes, the Hodrick-Prescott filter is preferable for I(2) series. |
| Keywords: | Business cycle, trend, time-series analysis, Hodrick-Prescott |
| JEL: | C22 E32 |
| Date: | 2005 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp1:3378&r=for |
| By: | Memmel, Christoph; Wehn, Carsten |
| Abstract: | The Value at Risk of a portfolio differs from the sum of the Values at Risk of the portfolio’s components. In this paper, we analyze the problem of how a single economic risk figure for the Value at Risk of a hypothetical portfolio composed of different commercial banks might be obtained for a supervisor. Using the daily profits and losses and the daily Value at Risk figures of twelve German banks for the period from 2001 to 2003, we estimate the Value at Risk of the entire portfolio. We assume a reduced-form model and neglect the effects of a potential bankruptcy of one of the banks. We analyze different models for the cross-correlation of the banks’ profits and losses. In an empirical study, we apply backtesting methods to determine which aggregation model leads to the best out-of-sample estimates for the portfolio’s economic risk figure. Our main findings can be summarized in three statements. (i) The portfolio’s Value at Risk can be estimated from time series data very well. (ii) During ‘normal’ times, the portfolio’s Value at Risk is much lower than the sum of the single Values at Risk. (iii) The relative marginal risk contribution depends on the bank in question and is between 0.05 and 0.62. |
| Keywords: | Value at Risk, portfolio, cross-correlation, market risk regulation, risk forecast, model validation |
| JEL: | C52 G11 G21 G28 |
| Date: | 2005 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp2:4257&r=for |
| By: | Philippe Méhaut (LEST - Laboratoire d'économie et de sociologie du travail - [CNRS : UMR6123] - [Université de Provence - Aix-Marseille I][Université de la Méditerranée - Aix-Marseille II]) |
| Abstract: | Finland and France share some common characteristics regarding the labour market situation and trends : a high level of unemployment (respectively 8.4% and 9.5%), a low rate of employment among the 55-65 and the 15-24 age groups (for the latter mainly due to a “full time” educational model), an ageing process with a growing level of retirements in the future (but with similar choices regarding the increasing age of retirement and level of provisions, and similar public policies regarding the decrease in early retirements), and young cohorts stable or slightly decreasing. In this context, forecasting labour demand and supply in the long run is a common concern, with the aim of producing some guidelines for labour market actors, for employment policy as well as for education and training policies. This paper will first outline some common trends and differences in the French experience regarding the forecasting tools. Then we will put the emphasis on common results and/or differences between the two countries. In the third part we will discuss the use of the forecasts' results mainly in the field of education and training policies. |
| Keywords: | Labour market; Education and training policies; Skill needs; Comparison; Finland; France |
| Date: | 2006–07–26 |
| URL: | http://d.repec.org/n?u=RePEc:hal:papers:halshs-00080198_v1&r=for |
| By: | Matthew T. Jones; Meral Karasulu |
| Abstract: | The objective of this paper is to provide a retrospective assessment of our ability to have predicted the impact of the 1997 crisis on the Korean corporate sector. We perform some simple stress tests on the aggregate balance sheets and income statements of the corporate sector to determine what could have been foreseen before the onset of the crisis. Our results show that data available in mid-1997 clearly showed that the corporate sector was very sensitive to various shocks, particularly interest rate shocks. Had stress tests been performed at the time, they would have revealed that the corporate sector was highly vulnerable to adverse economic developments. Our findings suggest that close surveillance of corporate sector balance sheets can play a useful role in understanding potential financial vulnerabilities. |
| Keywords: | Financial crisis , Korea, Republic of , Economic forecasting , Interest rates , Financial risk , |
| Date: | 2006–05–10 |
| URL: | http://d.repec.org/n?u=RePEc:imf:imfwpa:06/114&r=for |