Search results

Small-scale VARs are widely used in macroeconomics for forecasting US output, prices, and interest rates. However, recent work suggests these models may exhibit instabilities. As such, a variety of estimation or forecasting methods might be used to improve their forecast accuracy. These include using different observation windows for estimation, intercept correction, time-varying parameters, break dating, Bayesian shrinkage, model averaging, etc. This paper compares the effectiveness of such methods in real-time forecasting. We use forecasts from univariate time series models, the Survey of Professional Forecasters, and the Federal Reserve Board's Greenbook as benchmarks.

This chapter investigates the predictability of the European monetary policy through the eyes of the professional forecasters from a large investment bank. The analysis is based on forward-looking Actual and Perceived Taylor Rules for the European Central Bank which are estimated in real-time using a newly constructed database for the period April 2000–November 2009. The former policy rule is based on the actual refi rate set by the Governing Council, while the latter is estimated for the bank’s economists using their main point forecast for the upcoming refi rate decision as a dependent variable. The empirical evidence shows that the pattern of the refi rate is broadly well predicted by the professional forecasters even though the latter have foreseen more accurately the increases rather than the policy rate cuts. Second, the results point to an increasing responsiveness of the ECB to macroeconomic fundamentals along the forecast horizon. Third, the rolling window regressions suggest that the estimated coefficients have changed after the bankruptcy of Lehman Brothers in October 2008; the ECB has responded less strongly to macroeconomic fundamentals and the degree of policy inertia has decreased. A sensitivity analysis shows that the baseline results are robust to applying a recursive window methodology and some of the findings are qualitatively unaltered from using Consensus Economics forecasts in the regressions.

Recently, it has been suggested that macroeconomic forecasts from estimated dynamic stochastic general equilibrium (DSGE) models tend to be more accurate out-of-sample than random walk forecasts or Bayesian vector autoregression (VAR) forecasts. Del Negro and Schorfheide (2013) in particular suggest that the DSGE model forecast should become the benchmark for forecasting horse-races. We compare the real-time forecasting accuracy of the Smets and Wouters (2007) DSGE model with that of several reduced-form time series models. We first demonstrate that none of the forecasting models is efficient. Our second finding is that there is no single best forecasting method. For example, typically simple AR models are most accurate at short horizons and DSGE models are most accurate at long horizons when forecasting output growth, while for inflation forecasts the results are reversed. Moreover, the relative accuracy of all models tends to evolve over time. Third, we show that there is no support to the common practice of using large-scale Bayesian VAR models as the forecast benchmark when evaluating DSGE models. Indeed, low-dimensional unrestricted AR and VAR forecasts may forecast more accurately.

Accurate prediction of order demand across omni-channel supply chains improves the management's decision-making ability at strategic, tactical and operational levels. The paper aims to develop a predictive methodology for forecasting near-real-time e-commerce order arrivals in distribution centres, allowing third-party logistics service providers to manage the hour-to-hour fast-changing arrival rates of e-commerce orders better.

The paper proposes a novel machine learning predictive methodology through the integration of the time series data characteristics into the development of an adaptive neuro-fuzzy inference system. A four-stage implementation framework is developed for enabling practitioners to apply the proposed model.

A structured model evaluation framework is constructed for cross-validation of model performance. With the aid of an illustrative case study, forecasting evaluation reveals a high level of accuracy of the proposed machine learning approach in forecasting the arrivals of real e-commerce orders in three different retailers at three-hour intervals.

Results from the case study suggest that real-time prediction of individual retailer's e-order arrival is crucial in order to maximize the value of e-order arrival prediction for daily operational decision-making.

Earlier researchers examined supply chain demand, forecasting problem in a broader scope, particularly in dealing with the bullwhip effect. Prediction of real-time, hourly based order arrivals has been lacking. The paper fills this research gap by presenting a novel data-driven predictive methodology.

The paper seeks to evaluate accuracy and efficiency of consensus forecasts for all property rents and total returns in the UK. The aim of the paper is to investigate whether consensus forecasts, containing a high degree of judgement, are better than forecasts produced by uncomplicated time‐series and econometric models that practitioners can easily estimate and use for forecasting.

This study estimates simple models of all property rents and returns and generates forecasts for one‐ and two‐year horizons on a rolling basis over the period 1999 to 2004. These forecasts are real time forecasts. That is they are made using information available to the analyst at the time of the forecast each year and no future knowledge is assumed. The forecasts made by these models are compared with the corresponding consensus forecasts. The comparative assessment is based on conventional tests for bias, variability and efficiency of forecasts.

If attention is focused on rents, the consensus forecast is ranked best for the one‐year horizon but it is outperformed by the regression model and a combination of the statistical models for the two‐year horizon. For the one‐year and two‐year forecasts of total returns a simple regression model with interest rates clearly improves upon the consensus forecasts. There is clear evidence that the consensus forecasts fail to incorporate the information contained in recent interest rate movements. Therefore subject to the sample period for this analysis the survey forecasts of total returns cannot be considered impartial. Analysts should include base rate information into their predictions.

This is one of the few attempts to formally evaluate consensus forecasts in the real estate field and perform a direct comparison with quantitative forecasts. It produces initial evidence suggesting that highly judgemental consensus forecasts do not necessarily outperform quantitative forecasts based on fundamentals. It prompts property forecasters and investors to engage in forecast evaluation and include missing information and past errors in their forecasts.

Purpose – The purpose of this chapter is twofold: to forecast gross domestic product (GDP) using nonparametric method, known as multivariate k-nearest neighbors method, and to provide asymptotic properties for this method.

Methodology/approach – We consider monthly and quarterly macroeconomic variables, and to match the quarterly GDP, we estimate the missing monthly economic variables using multivariate k-nearest neighbors method and parametric vector autoregressive (VAR) modeling. Then linking these monthly macroeconomic variables through the use of bridge equations, we can produce nowcasting and forecasting of GDP.

Findings – Using multivariate k-nearest neighbors method, we provide a forecast of the euro area monthly economic indicator and quarterly GDP, which is better than that obtained with a competitive linear VAR modeling. We also provide the asymptotic normality of this k-nearest neighbors regression estimator for dependent time series, as a confidence interval for point forecast in time series.

Originality/value of chapter – We provide a new theoretical result for nonparametric method and propose a novel methodology for forecasting using macroeconomic data.

This article surveys recent developments in the evaluation of point and density forecasts in the context of forecasts made by vector autoregressions. Specific emphasis is placed on highlighting those parts of the existing literature that are applicable to direct multistep forecasts and those parts that are applicable to iterated multistep forecasts. This literature includes advancements in the evaluation of forecasts in population (based on true, unknown model coefficients) and the evaluation of forecasts in the finite sample (based on estimated model coefficients). The article then examines in Monte Carlo experiments the finite-sample properties of some tests of equal forecast accuracy, focusing on the comparison of VAR forecasts to AR forecasts. These experiments show the tests to behave as should be expected given the theory. For example, using critical values obtained by bootstrap methods, tests of equal accuracy in population have empirical size about equal to nominal size.

Describes a tracer model, DREAM (the Danish Rimpuff and Eulerian Accidental release Model), developed for studying transport, dispersion, and deposition of air pollution caused by a single but strong source. The model is based on a combination of a Lagrangian short‐range puff model and a Eulerian long‐range transport model. It has been run and validated against measurements from the two European Tracer Experiment (ETEX) releases and from the Chernobyl accident. An air pollution forecast system, THOR, is under development, to make forecasts of various air pollutants on a European scale. Some preliminary results are shown. DREAM will be implemented in THOR for calculations of real time predictions of transport, dispersion and deposition of radioactive material from accidental releases (e.g. Chernobyl). Some applications of the DREAM model and examples of model results are described.

Forecasts from dynamic factor models potentially benefit from refining the data set by eliminating uninformative series. This paper proposes to use prediction weights as provided by the factor model itself for this purpose. Monte Carlo simulations and an empirical application to short-term forecasts of euro area, German, and French GDP growth from unbalanced monthly data suggest that both prediction weights and least angle regressions result in improved nowcasts. Overall, prediction weights provide yet more robust results.

We develop a theoretical model to compare forecast uncertainty estimated from time-series models to those available from survey density forecasts. The sum of the average variance of individual densities and the disagreement is shown to approximate the predictive uncertainty from well-specified time-series models when the variance of the aggregate shocks is relatively small compared to that of the idiosyncratic shocks. Due to grouping error problems and compositional heterogeneity in the panel, individual densities are used to estimate aggregate forecast uncertainty. During periods of regime change and structural break, ARCH estimates tend to diverge from survey measures.