nep-for New Economics Papers
on Forecasting
Issue of 2006‒07‒28
nine papers chosen by
Rob J Hyndman
Monash University

  1. Detecting and predicting forecast breakdowns. By Raffaella Giacomini; Barbara Rossi
  2. Forecasting regional labor market developments under spatial heterogeneity and spatial correlation By Longhi, Simonetta; Nijkamp, Peter
  3. Nowcasting GDP and inflation: the real-time informational content of macroeconomic data releases. By David H. Small; Domenico Giannone; Lucrezia Reichlin
  4. Inflation forecast-based-rules and indeterminacy: a puzzle and a resolution. By Paul Levine; Peter McAdam; Joseph Pearlman
  5. Inflation Expectations and Regime Shifts By Matti Viren
  6. Transparency, expectations, and forecasts. By Robert A. Eisenbeis; Andy Bauer; Daniel F. Waggoner; Tao A. Zha
  7. Time-Varying Quantiles By Giuliano De Rossi; Andrew Harvey
  8. Estimating The Impacts of Demographic and Policy Changes On Pension Deficit A Simple Method and Application to China By Zeng Yi
  9. The Dutch block of the ESCB multi-country model. By Matteo Ciccarelli; Elena Angelini; Frédéric Boissay

  1. By: Raffaella Giacomini (Department of Economics, UCLA, Box 951477, Los Angeles, CA 90095-1477, USA.); Barbara Rossi (Department of Economics, Duke University, Durham NC27708, USA.)
    Abstract: We propose a theoretical framework for assessing whether a forecast model estimated over one period can provide good forecasts over a subsequent period. We formalize this idea by defining a forecast breakdown as a situation in which the out-of-sample performance of the model, judged by some loss function, is significantly worse than its in-sample performance. Our framework, which is valid under general conditions, can be used not only to detect past forecast breakdowns but also to predict future ones. We show that main causes of forecast breakdowns are instabilities in the data generating process and relate the properties of our forecast breakdown test to those of existing structural break tests. The empirical application finds evidence of a forecast breakdown in the Phillips’ curve forecasts of U.S. inflation, and links it to inflation volatility and to changes in the monetary policy reaction function of the Fed. JEL Classification: C22; C52; C53.
    Keywords: Structural change; forecast evaluation; forecast rationality testing; in-sample evaluation; out-of-sample evaluation.
    Date: 2006–06
  2. By: Longhi, Simonetta (Vrije Universiteit Amsterdam, Faculteit der Economische Wetenschappen en Econometrie (Free University Amsterdam, Faculty of Economics Sciences, Business Administration and Economitrics); Nijkamp, Peter
    Abstract: Because of heterogeneity across regions, economic policy measures are increasingly targeted at the regional level, and the need for forecasts at the regional level is rapidly increasing. The data available to compute regional forecasts is usually based on a pseudo-panel of a limited number of observations over time, and a large number of areas (regions) strongly interacting with each other. The application of traditional time-series techniques to distinct time series of regional data is likely to be a suboptimal forecasting strategy. In the field of regional forecasting of socioeconomic variables, both linear and nonlinear models have recently been applied and evaluated. However, often such analyses ignore the spatial interactions among regions. We evaluate the ability of different statistical techniques - namely spatial error and spatial cross-regressive models - to correct for misspecifications due to neglected spatial correlation in the data. Our empirical application concerns short-term forecasts of employment in 326 West German regions; we find that the superimposed spatial structure that is required for the estimation of spatial models improves the forecasting performance of non-spatial models.
    Keywords: Space-Time Data; Regional Forecasts; Spatial Heterogeneity; Spatial Correlation
    JEL: R12 C53
    Date: 2006
  3. By: David H. Small (Federal Reserve Board - Monetary Studies Section, 20th and C Streets, NW, Washington , DC 20551, United States.); Domenico Giannone (Free University of Brussels (VUB/ULB), European Center for Advanced Research in Economics and Statistics (ECARES), Ave. Franklin D Roosevelt, 50 - C.P. 114, B-1050 Brussels, Belgium.); Lucrezia Reichlin (Free University of Brussels (VUB/ULB), European Center for Advanced Research in Economics and Statistics (ECARES), Ave. Franklin D Roosevelt, 50 - C.P. 114, B-1050 Brussels, Belgium.)
    Abstract: This paper formalizes the process of updating the nowcast and forecast on output and inflation as new releases of data become available. The marginal contribution of a particular release for the value of the signal and its precision is evaluated by computing news on the basis of an evolving conditioning information set. The marginal contribution is then split into what is due to timeliness of information and what is due to economic content. We find that the Federal Reserve Bank of Philadelphia surveys have a large marginal impact on the nowcast of both inflation variables and real variables and this effect is larger than that of the Employment Report. When we control for timeliness of the releases, the effect of hard data becomes sizeable. Prices and quantities affect the precision of the estimates of inflation while GDP is only affected by real variables and interest rates. JEL Classification: E52; C33; C53.
    Keywords: Forecasting; monetary policy; factor model; real time data; large data sets; news.
    Date: 2006–05
  4. By: Paul Levine (University of Surrey - Department of Economics, Guildford, Surrey GU2 7XH, United Kingdom.); Peter McAdam (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.); Joseph Pearlman (London Metropolitan University, Department of Economics, Finance and International Business, 31Jewry Street, London EC3N 2EY, United Kingdom.)
    Abstract: We examine an interesting puzzle in monetary economics between what monetary authorities claim (namely to be forward-looking and pre-emptive) and the poor stabilization properties routinely reported for forecast-based-rules. Our resolution is that central banks should be viewed as following 'Calvo-type' inflation-forecast-based(IFB)interest rate rules which depend on a discounted sum of current and future rates of inflation. Such rules might be regarded as both within the legal frame- works, and potentially mimicking central bankers' practice. We find that Calvo-type IFB interest rate rules are first - less prone to indeterminacy than standard rules with a finite forward horizon. Second, for such rules in difference form, the indeterminacy problem disappears altogether. Third, optimized forms have good stabilization properties as they become more forward-looking, a property that sharply contrasts that of standard IFB rules. Fourth, they appear data coherent when incorporated into a well-known estimated DSGE model of the Euro-area. JEL Classification: E52; E37; E58.
    Keywords: Inflation-forecast-based interest rate rules; Calvo-type interest rate rules.
    Date: 2006–06
  5. By: Matti Viren (Department of Economics, University of Turku)
    Abstract: This paper focuses on the determination of inflation expectations. The following two questions are examined: How much do inflation expectations reflect different economic and institutional regime shifts and in which way do inflation expectations adjust to past inflation? The basic idea in the analysis is an assumption that inflation expectations do not mechanically reflect past inflation as may econometric specification de facto assume but rather they depend on the relevant economic regime. Also the adjustment of expectations to past inflation is different in different inflation regimes. The regime analysis is based on panel data from EMU/EU countries for the period 1973–2004, while the inflation adjustment analysis mainly uses the Kalman filter technique for individual countries for the same period. Expectations (forecasts) are derived from OECD data. Empirical results strongly favour the regime-sensitivity hypothesis and provide an explanation for the poor performance of conventional estimation procedures in the context of Phillips curves
    Keywords: inflation expectations, Kalman filter, stability
    JEL: E32 E37
    Date: 2006–04
  6. By: Robert A. Eisenbeis (Federal Reserve Bank of Atlanta, 1000 Peachtree Street N.E., Atlanta, GA 30309-4470, United States.); Andy Bauer (Federal Reserve Bank of Atlanta, 1000 Peachtree Street N.E., Atlanta, GA 30309-4470, United States.); Daniel F. Waggoner (Federal Reserve Bank of Atlanta, 1000 Peachtree Street N.E., Atlanta, GA 30309-4470, United States.); Tao A. Zha (Federal Reserve Bank of Atlanta, 1000 Peachtree Street N.E., Atlanta, GA 30309-4470, United States.)
    Abstract: In 1994 the FOMC began to release statements after each meeting. This paper investigates whether the public's views about the current path of the economy and of future policy have been affected by changes in the Federal Reserve's communications policy as reflected in private sector's forecasts of future economic conditions and policy moves. In particular, has the ability of private agents to predict where the economy is going improved since 1994? If so, on which dimensions has the ability to forecast improved? We find evidence that the individuals' forecasts have been more synchronized since 1994, implying the possible effects of the FOMC's transparency. On the other hand, we find little evidence that the common forecast errors, which are the driving force of overall forecast errors, have become smaller since 1994. JEL Classification: E59; C33.
    Keywords: Transparency; common errors; idiosyncratic errors.
    Date: 2006–06
  7. By: Giuliano De Rossi; Andrew Harvey
    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. Quantiles estimated in this way provide information on various aspects of a time series, including dispersion, asymmetry and, for financial applications, value at risk. Tests for the constancy of quantiles, and associated contrasts, are constructed using indicator variables; these tests have a similar form to stationarity tests and, under the null hypothesis, their asymptotic distributions belong to the Cramér von Mises family. Estimates of the quantiles at the end of the series provide the basis for forecasting. As such they offer an alternative to conditional quantile autoregressions and, at the same time, give some insight into their structure and potential drawbacks.
    Keywords: Dispersion; quantile regression; signal extraction; state space smoother; stationarity tests; value at risk.
    JEL: C14 C22
    Date: 2006–07
  8. By: Zeng Yi (Center for Demographic Studies and Department of Sociology, Duke University China Center for Economic Research, Peking University)
    Abstract: This article derives a simple method for projecting pension deficit as percent of GDP in future years based on commonly available population forecasting and a few predictable economic and policy variables. Compared with the classic basic equilibrium equation of pension funds, our new formula decomposes the retirees-workers ratio which mixes various kinds of impacts into three more-easily-predictable variables – the elderly dependent ratio, the prevalence of pension coverage, and the employment rate. Our illustrative application to China shows that gradually increasing the current low minimum age of retirement will largely reduce the pension deficit, under various demographic regimes. The pension deficit as % of GDP in the low fertility scenarios (which corresponds with keeping the current rigid fertility control policy unchanged in the longrun)would be 5.6-11.1, 3.8-6.3, and 9.0-13.8 times as high as that in the Medium Fertility & Medium Mortality scenarios in 2040, 2060, and 2080
  9. By: Matteo Ciccarelli (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.); Elena Angelini (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.); Frédéric Boissay (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.)
    Abstract: The paper presents the Dutch country block of the ESCB Multi-Country Model(MCM) for the euro area. We show how a theoretical model is translated into an econometric specification and how this specification is in turn estimated and used in the projection exercises of the E(S)CB. The dynamic properties of the model are analyzed and the effects of six exogenous shocks to the economy discussed. The long run simulations performed deliver responses of the baseline economy in line with both macroeconomic theory and practice, from a quantitative and a qualitative point of view. JEL Classification: C3; C5; E1; E2.
    Keywords: Multi-country model; forecast; simulation; Netherlands.
    Date: 2006–06

This nep-for issue is ©2006 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.