Assessing the Macroeconomic Forecasting Performance of Boosting: Evidence for the United States,the Euro Area and Germany

The use of large datasets for macroeconomic forecasting has received a great deal of interest recently. Boosting is one possible method of using high‐dimensional data for this purpose. It is a stage‐wise additive modelling procedure, which, in a linear specification, becomes a variable selection device that iteratively adds the predictors with the largest contribution to the fit. Using data for the United States, the euro area and Germany, we assess the performance of boosting when forecasting a wide range of macroeconomic variables. Moreover, we analyse to what extent its forecasting accuracy depends on the method used for determining its key regularization parameter: the number of iterations. We find that boosting mostly outperforms the autoregressive benchmark, and that K‐fold cross‐validation works much better as stopping criterion than the commonly used information criteria. Copyright © 2014 John Wiley & Sons, Ltd.     

Forecasting euro area variables with German pre‐EMU data

It is investigated whether euro area variables can be forecast better based on synthetic time series for the pre‐euro period or by using just data from Germany for the pre‐euro period. Our forecast comparison is based on quarterly data for the period 1970Q1–2003Q4 for 10 macroeconomic variables. The years 2000–2003 are used as forecasting period. A range of different univariate forecasting methods is applied. Some of them are based on linear autoregressive models and we also use some nonlinear or time‐varying coefficient models. It turns out that most variables which have a similar level for Germany and the euro area such as prices can be better predicted based on German data, while aggregated European data are preferable for forecasting variables which need considerable adjustments in their levels when joining German and European Monetary Union (EMU) data. These results suggest that for variables which have a similar level for Germany and the euro area it may be reasonable to consider the German pre‐EMU data for studying economic problems in the euro area. Copyright © 2008 John Wiley & Sons, Ltd.     

Forecasting stock market volatility using (non-linear) Garch models

In this paper we study the performance of the GARCH model and two of its non-linear modifications to forecast weekly stock market volatility. The models are the Quadratic GARCH (Engle and Ng, 1993) and the Glosten, Jagannathan and Runkle (1992) models which have been proposed to describe, for example, the often observed negative skewness in stock market indices. We find that the QGARCH model is best when the estimation sample does not contain extreme observations such as the 1987 stock market crash and that the GJR model cannot be recommended for forecasting.     

日径流预报贝叶斯回声状态网络方法

回声状态网络（ESN）相比传统递归神经网络,具有模型简单、参数训练速度快的特点．针对标准ESN因常采用线性回归率定模型参数容易出现过拟合问题,提出了基于贝叶斯回声状态网络（BESN）的日径流预报模型．该模型将贝叶斯理论与ESN模型相结合,通过权重后验概率密度最大化而获得最优输出权重,提高了模型的泛化能力．通过安砂和新丰江两座水库日径流预测实例表明,BESN模型是一种有效、可行的预测方法,与传统BP神经网络和ESN模型对比,进一步表明BESN模型具有更好的预测精度．     

Forecasting with more than one model

This paper comprises an editorial review for the Special Issue on Combining Forecasts. It gives a background to the current growth of interest in this topic and speculates upon some of the reasons for this popularity. Some of the main methodological issues in practice are also described.     

Forecasting car expenditures using household survey data

Surveys collecting data on consumer attitudes and buying intentions have been performed in Sweden since 1973. This paper examines the usefulness of these data as quick indicators of the development of household expenditures on automobiles. In the evaluation we are considering the explanatory power as well as the prediction accuracy. It turns out that the best single indicator is among the plan indices. However, an indicator based on car registration statistics is found to be at least as good. By combining plan/attitude indices with car registrations our study shows that considerable improvements can be obtained.     

Bayesian Analysis of Vector ARMA Models using Gibbs Sampling

We present a methodology for estimation, prediction, and model assessment of vector autoregressive moving-average (VARMA) models in the Bayesian framework using Markov chain Monte Carlo algorithms. The sampling-based Bayesian framework for inference allows for the incorporation of parameter restrictions, such as stationarity restrictions or zero constraints, through appropriate prior specifications. It also facilitates extensive posterior and predictive analyses through the use of numerical summary statistics and graphical displays, such as box plots and density plots for estimated parameters. We present a method for computationally feasible evaluation of the joint posterior density of the model parameters using the exact likelihood function, and discuss the use of backcasting to approximate the exact likelihood function in certain cases. We also show how to incorporate indicator variables as additional parameters for use in coefficient selection. The sampling is facilitated through a Metropolis–Hastings algorithm. Graphical techniques based on predictive distributions are used for informal model assessment. The methods are illustrated using two data sets from business and economics. The first example consists of quarterly fixed investment, disposable income, and consumption rates for West Germany, which are known to have correlation and feedback relationships between series. The second example consists of monthly revenue data from seven different geographic areas of IBM. The revenue data exhibit seasonality, strong inter-regional dependence, and feedback relationships between certain regions.© 1997 John Wiley & Sons, Ltd.     

Forecasting with preliminary data

This paper examines several methods to forecast revised US trade balance figures by incorporating preliminary data. Two benchmark forecasts are considered: one ignoring the preliminary data and the other applying a combination approach; with the second outperforming the first. Competing models include a bivariate AR error-correction model and a bivariate AR error-correction model with GARCH effects. The forecasts from the latter model outperforms the combination benchmark for the one-step forecast case only. A restricted AR error-correction model with GARCH effects is discovered to provide the best forecasts. © 1997 John Wiley & Sons, Ltd.     

Forecasting with growth curves: the effect of error structure

"The main theme of this paper is an investigation into the importance of error structure as a determinant of the forecasting accuracy of the logistic model. The relationship between the variance of the disturbance term and forecasting accuracy is examined empirically. A general local logistic model is developed as a vehicle to be used in this investigation. Some brief comments are made on the assumptions about error structure, implicit or explicit, in the literature." The results suggest that "the variance of the disturbance term, when using the logistic to forecast human populations, is proportional to at least the square of population size."     

Forecasting the Antwerp maritime traffic flows using transformations and intervention models

This article uses univariate time-series models with data transformations and intervention models to forecast the volumes of twenty-two maritime traffic flows in the port of Antwerp which are expressed in tonnes. The models obtained produce forecasts that are a substantial improvement over those obtained with unadjusted data. The models also provide useful insight into the behaviour of maritime traffic flows during the period 1971–82.     

Forecasting time series with increasing seasonal variation

Four options for modeling and forecasting time series data containing increasing seasonal variation are discussed, including data transformations, double seasonal difference models and two kinds of transfer function-type ARIMA models employing seasonal dummy variables. An explanation is given for the typical ARIMA model identification analysis failing to identify double seasonal difference models for this kind of data. A logical process of selecting one option for a particular case is outlined, focusing on issues of linear versus non-linear increasing seasonal variation, and the level of stochastic versus deterministic behavior in a time series. Example models for the various options are presented for six time series, with point forecast and interval forecast comparisons. Interval forecasts from data-transformation models are found to generally be too wide and sometimes illogical in the dependence of their width on the point forecast level. Suspicion that maximum likelihood estimation of ARIMA models leads to excessive indications of unit roots in seasonal moving-average operators is reported.     

Forecasting exchange rates using cointegration models and intra‐day data

We present a cointegration analysis on the triangle (USD–DEM, USD–JPY, DEM–JPY) of foreign exchange rates using intra‐day data. A vector autoregressive model is estimated and evaluated in terms of out‐of‐sample forecast accuracy measures. Its economic value is measured on the basis of trading strategies that account for transaction costs. We show that the typical seasonal volatility in high‐frequency data can be accounted for by transforming the underlying time scale. Results are presented for the original and the modified time scales. We find that utilizing the cointegration relation among the exchange rates and the time scale transformation improves forecasting results. Copyright © 2002 John Wiley & Sons, Ltd.     

Forecasting inflation using economic indicators: the case of France

In order to provide short‐run forecasts of headline and core HICP inflation for France, we assess the forecasting performance of a large set of economic indicators, individually and jointly, as well as using dynamic factor models. We run out‐of‐sample forecasts implementing the Stock and Watson (1999) methodology. We find that, according to usual statistical criteria, the combination of several indicators—in particular those derived from surveys—provides better results than factor models, even after pre‐selection of the variables included in the panel. However, factors included in VAR models exhibit more stable forecasting performance over time. Results for the HICP excluding unprocessed food and energy are very encouraging. Moreover, we show that the aggregation of forecasts on subcomponents exhibits the best performance for projecting total inflation and that it is robust to data snooping. Copyright © 2007 John Wiley & Sons, Ltd.     

Inflation forecasting for aggregates of the EU-7 and EU-14 with Bayesian VAR models

This article applies the Bayesian Vector Auto-Regressive (BVAR) model to key economic aggregates of the EU-7, consisting of the former narrow-band ERM members plus Austria, and the EU-14. This model appears to be useful as an additional forecasting tool besides structural macroeconomic models, as is shown both by absolute forecasting performance and by a comparison of ex-post BVAR forecasts with forecasts by the OECD. A comparison of the aggregate models to single-country models reveals that pooling has a strong impact on forecast errors. If forecast errors are interpreted as shocks, shocks appear to be—at least in part—asymmetric, or countries react differently to shocks. © 1998 John Wiley & Sons, Ltd.     

Real‐time or current vintage: does the type of data matter for forecasting and model selection?

In this paper we investigate the impact of data revisions on forecasting and model selection procedures. A linear ARMA model and nonlinear SETAR model are considered in this study. Two Canadian macroeconomic time series have been analyzed: the real‐time monetary aggregate M3 (1977–2000) and residential mortgage credit (1975–1998). The forecasting method we use is multi‐step‐ahead non‐adaptive forecasting. Copyright © 2008 John Wiley & Sons, Ltd.     

Forecasting us home sales using bvar models and survey data on households' buying attitudes for homes

This study uses Bayesian vector autoregressive models to examine the usefulness of survey data on households' buying attitudes for homes in predicting sales of homes. We find a negligible deterioration in the accuracy of forecasts of home sales when buying attitudes are dropped from a model that includes the price of homes, the mortgage rate, real personal disposable income, and die unemployment rate. This suggests that buying attitudes do not add much to the information contained in these variables. We also find that forecasts from the model that includes both buying attitudes and the aforementioned variables are similar to those generated from a model that excludes the survey data but contains the other variables. Additionally, the variance decompositions suggest that the gain from including the survey data in the model that already contains other economic variables is small.