nep-for New Economics Papers
on Forecasting
Issue of 2007‒05‒12
ten papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting with Factors: The Accuracy of Timeliness By Christian Gillitzer; Jonathan Kearns
  2. A New Approach to Forecasting Exchange Rates By Kenneth W Clements; Yihui Lan
  3. An Evaluation of the Exchange Rate Forecasting Performance of the New Keynesian Model By Vitek, Francis
  4. Nowcasting an Economic Aggregate with Disaggregate Dynamic Factors: An Application to Portuguese GDP By António José Morgado; Luis Catela Nunes; Susana Salvado
  5. Does Age Structure Forecast Economic Growth? By David E. Bloom; David Canning; Günther Fink; Jocelyn Finlay
  6. Inflation in Croatia with outlook to future By Paunić, Alida
  7. The Instrument-Rate Projection under Inflation Targeting: The Norwegian Example By Lars E.O. Svensson
  8. Do sentiment indicators help to assess and predict actual developments of the Chinese economy? By Mehrotra, Aaron; Rautava, Jouko
  9. A note on model selection in (time series) regression models - General-to-specific or specific-to-general? By Herwartz, Helmut
  10. A flexible approach to parametric inference in nonlinear time series models By Gary Koop; Simon Potter

  1. By: Christian Gillitzer (Reserve Bank of Australia); Jonathan Kearns (Reserve Bank of Australia)
    Abstract: This paper demonstrates that factor-based forecasts for key Australian macroeconomic series can outperform standard time-series benchmarks. In practice, however, the advantages of using large panels of data to construct the factors typically comes at the cost of using less timely series, thereby delaying when the forecasts can be made. To produce more timely forecasts it is possible to use a narrower data panel, though this will possibly result in less accurate factor estimates and so less accurate forecasts. We demonstrate this trade-off between accuracy and timeliness with out-of-sample forecasts. With the exception of only consumer price inflation, the forecasts do not become less accurate as they utilise less information by excluding less timely series. So while factor forecasts have large data requirements, we show that these should not prevent their practical use when timely forecasts are needed.
    Keywords: forecasting; factor models; Australia
    JEL: C53 E27 E37
    Date: 2007–04
  2. By: Kenneth W Clements (UWA Business School, The University of Western Australia); Yihui Lan (UWA Business School, The University of Western Australia)
    Abstract: Building on purchasing power parity theory, this paper proposes a new approach to forecasting exchange rates using the Big Mac data from The Economist magazine. Our approach is attractive in three aspects. Firstly, it uses easily-available Big Mac prices as input. These prices avoid several serious problems associated with broad price indexes, such as the CPI, that are used in conventional PPP studies. Secondly, this approach provides real-time exchange-rate forecasts at any forecast horizon. Such real-time forecasts can be made on a day-to-day basis if required, so that the forecasts are based on the most up-to-date information set. These high-frequency forecasts could be particularly appealing to decision makers who want up-to-date forecasts of exchange rates. Finally, as our forecasts are obtained through Monte Carlo simulation, estimation uncertainty is made explicit in our framework which provides the entire distribution of exchange rates, not just a single point estimate. A comparison of our forecasts with the random walk model shows that although the random walk is superior for very short horizons, our approach tends to dominate over the medium to longer term.
    Keywords: Exchange-rate forecasting, Bic Mac prices, purchasing power parity, Monte Carlo simulation
    JEL: F30 C53
    Date: 2006
  3. By: Vitek, Francis
    Abstract: This paper evaluates the dynamic out of sample nominal exchange rate forecasting performance of the canonical New Keynesian model of a small open economy. A novel Bayesian procedure for jointly estimating the hyperparameters and trend components of a state space representation of an approximate linear panel unobserved components representation of this New Keynesian model, conditional on prior information concerning the values of hyperparameters and trend components, is developed and applied for this purpose. In agreement with the existing empirical literature, we find that nominal exchange rate movements are difficult to forecast, with a random walk generally dominating the canonical New Keynesian model of a small open economy in terms of predictive accuracy at all horizons. Nevertheless, we find empirical support for the common practice in the theoretical open economy macroeconomics literature of imposing deterministic equality restrictions on deep structural parameters across economies, both in sample and out of sample.
    Keywords: Exchange rate forecasting; New Keynesian model; Small open economy
    JEL: C13 C11 F41 F47 C33
    Date: 2007–04–17
  4. By: António José Morgado (GEE, Ministério da Economia e da Inovação; Faculdade de Economia, Universidade Nova de Lisboa); Luis Catela Nunes (Faculdade de Economia, Universidade Nova de Lisboa); Susana Salvado (GEE, Ministério da Economia e da Inovação; Faculdade de Economia, Universidade Nova de Lisboa)
    Abstract: This paper consists of an empirical study comparing a dynamic factor model approach to estimate the current quarter aggregate GDP with the alternative approach of aggregating the forecasts obtained from specific dynamic factor models for each major expenditure disaggregate. The out-of-sample forecasting performance results suggest that there is no advantage in aggregating the disaggregate forecasts.
    Keywords: Forecasting; Dynamic Factor Model; Temporal Disaggregation
    JEL: C53 C82
    Date: 2007–02
  5. By: David E. Bloom; David Canning; Günther Fink; Jocelyn Finlay (Harvard School of Public Health)
    Abstract: High ratios of working age to dependent population can yield a increases the rate of economic growth. We estimate the parameters model with a cross section of countries over the period 1960 to 1980 inclusion of age structure improves the model’s forecasts for the period that including age structure improves the forecast, although there instability between periods with an unexplained growth slowdown the model to generate growth forecasts for the period 2000–2020.
    Keywords: Economic Growth, Demography, Forecast Evaluation, Error Decomposition, Panel Analysis.
    Date: 2006–12
  6. By: Paunić, Alida
    Abstract: Central Banks have gained much credibility in controlling one important macroeconomic variable: inflation. This paper tries to examine the relation between inflation and other economic variables in Croatia by searching for the best forecasting model.
    Keywords: inflation; modeling; unemployment
    JEL: E31 C53 C51
    Date: 2007–05
  7. By: Lars E.O. Svensson (Princeton University, CEPR, and NBER)
    Abstract: The introduction of inflation targeting has led to major progress in practical monetary policy. Recent debate has focused on the interest-rate assumption underlying published projections of inflation and other target variables. This paper discusses the role of alternative interest-rate paths in the monetary-policy decision process and the recent publication by Norges Bank (the central bank of Norway) of optimal interest-rate projections with fan charts.
    Keywords: Forecasts, flexible inflation targeting, optimal monetary policy.
    JEL: E42 E52 E58
    Date: 2006–05
  8. By: Mehrotra, Aaron (BOFIT); Rautava, Jouko (BOFIT)
    Abstract: This paper evaluates the usefulness of business sentiment indicators for forecasting developments in the Chinese real economy. We use data on diffusion indices collected by the People’s Bank of China for forecasting industrial production, retail sales and exports. Our bivariate vector autoregressive models, each composed of one diffusion index and one real sector variable, generally outperform univariate AR models in forecasting one to four quarters ahead. Similarly, principal components analysis, combining information from various diffusion indices, leads to enhanced forecasting performance. Our results indicate that Chinese business sentiment indicators convey useful information about current and future developments in the real economy. They also suggest that the official data provide a fairly accurate picture of the Chinese economy.
    Keywords: forecasting; diffusion index; VAR; China
    JEL: E32 E37 P27
    Date: 2007–05–04
  9. By: Herwartz, Helmut
    Abstract: The paper provides Monte Carlo evidence on the performance of general-to-specific and specific-to-general selection of explanatory variables in linear (auto)regressions. In small samples the former is markedly inefficient in terms of ex-ante forecasting performance.
    Keywords: Model selection, specification testing, Lagrange multiplier tests
    JEL: C22 C51
    Date: 2007
  10. By: Gary Koop; Simon Potter
    Abstract: Many structural break and regime-switching models have been used with macroeconomic and financial data. In this paper, we develop an extremely flexible parametric model that accommodates virtually any of these specifications?and does so in a simple way that allows for straightforward Bayesian inference. The basic idea underlying our model is that it adds two concepts to a standard state space framework. These ideas are ordering and distance. By ordering the data in different ways, we can accommodate a wide range of nonlinear time series models. By allowing the state equation variances to depend on the distance between observations, the parameters can evolve in a wide variety of ways, allowing for models that exhibit abrupt change as well as those that permit a gradual evolution of parameters. We show how our model will (approximately) nest almost every popular model in the regime-switching and structural break literatures. Bayesian econometric methods for inference in this model are developed. Because we stay within a state space framework, these methods are relatively straightforward and draw on the existing literature. We use artificial data to show the advantages of our approach and then provide two empirical illustrations involving the modeling of real GDP growth.
    Keywords: Time-series analysis ; Econometric models ; Economic forecasting
    Date: 2007

This nep-for issue is ©2007 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.