http://repub.eur.nl/res/aut/21846/ List of Publications en http://repub.eur.nl/static-eur/img/logo.png http://repub.eur.nl http://repub.eur.nl/res/pub/37989/ 2013-04-01T00:00:00Z This paper compares various ways of extracting macroeconomic information from a data-rich environment for forecasting the yield curve using the Nelson-Siegel model. Five issues in extracting factors from a large panel of macro variables are addressed; namely, selection of a subset of the available information, incorporation of the forecast objective in constructing factors, specification of a multivariate forecast objective, data grouping before constructing factors, and selection of the number of factors in a data-driven way. Our empirical results show that each of these features helps to improve forecast accuracy, especially for the shortest and longest maturities. Factor-augmented methods perform well in relatively volatile periods, including the crisis period in 2008-9, when simpler models do not suffice. The macroeconomic information is exploited best by partial least squares methods, with principal component methods ranking second best. Reductions of mean squared prediction errors of 20-30% are attained, compared to the Nelson-Siegel model without macro factors. http://repub.eur.nl/res/pub/30794/ 2011-12-13T00:00:00Z This thesis discusses various novel techniques for economic forecasting. The focus is on methods that exploit the information in large data sets effectively. Each of these methods is compared to established techniques for forecasting yields on U.S. Treasury Bills, housing prices, industrial production, the employment rate, and several other economic quantities. In general, major improvements in forecast quality are obtained. Broadly speaking, two diff erent approaches can be taken when dealing with large data sets: summarizing the data before estimating a model, or restricting the model parameters suffi ciently so that all data can be used. This thesis presents advances in both directions. In particular, a new technique for summarizing large data sets in the presence of outlying observations is proposed, as well as a method for estimating fl exible nonlinear models with many predictors. The usefulness of these techniques is demonstrated, both in simulation experiments and in empirical applications. Peter Exterkate (1985) graduated from Tinbergen Institute’s M.Phil. programme in 2008, with honors. His research interests include the empirical modelling and forecasting of fi nancial time series, analysis of large data sets, nonlinear techniques, and robust methods. Part of his research is forthcoming in Journal of Forecasting. Currently, Peter works as a post-doctoral researcher at the Center for Research in Econometric Analysis of Time Series (CREATES) at Aarhus University, Denmark. http://repub.eur.nl/res/pub/26508/ 2011-09-01T00:00:00Z Kernel ridge regression is gaining popularity as a data-rich nonlinear forecasting tool, which is applicable in many different contexts. This paper investigates the influence of the choice of kernel and the setting of tuning parameters on forecast accuracy. We review several popular kernels, including polynomial kernels, the Gaussian kernel, and the Sinc kernel. We interpret the latter two kernels in terms of their smoothing properties, and we relate the tuning parameters associated to all these kernels to smoothness measures of the prediction function and to the signal-to-noise ratio. Based on these interpretations, we provide guidelines for selecting the tuning parameters from small grids using cross-validation. A Monte Carlo study confirms the practical usefulness of these rules of thumb. Finally, the flexible and smooth functional forms provided by the Gaussian and Sinc kernels makes them widely applicable, and we recommend their use instead of the pop ular polynomial kernels in general settings, in which no information on the data-generating process is available. http://repub.eur.nl/res/pub/25712/ 2011-07-25T00:00:00Z Factor construction methods are widely used to summarize a large panel of variables by means of a relatively small number of representative factors. We propose a novel factor construction procedure that enjoys the properties of robustness to outliers and of sparsity; that is, having relatively few nonzero factor loadings. Compared to more traditional factor construction methods, we find that this procedure leads to better interpretable factors and to a favorable forecasting performance, both in a Monte Carlo experiment and in two empirical applications to large data sets, one from macroeconomics and one from microeconomics. http://repub.eur.nl/res/pub/22335/ 2011-01-04T00:00:00Z This paper puts forward kernel ridge regression as an approach for forecasting with many predictors that are related nonlinearly to the target variable. In kernel ridge regression, the observed predictor variables are mapped nonlinearly into a high-dimensional space, where estimation of the predictive regression model is based on a shrinkage estimator to avoid overfitting. We extend the kernel ridge regression methodology to enable its use for economic time-series forecasting, by including lags of the dependent variable or other individual variables as predictors, as is typically desired in macroeconomic and financial applications. Monte Carlo simulations as well as an empirical application to various key measures of real economic activity confirm that kernel ridge regression can produce more accurate forecasts than traditional linear methods for dealing with many predictors based on principal component regression. http://repub.eur.nl/res/pub/18254/ 2010-02-23T00:00:00Z Various ways of extracting macroeconomic information from a data-rich environment are compared with the objective of forecasting yield curves using the Nelson-Siegel model. Five issues in factor extraction are addressed, namely, selection of a subset of the available information, incorporation of the forecast objective in constructing factors, specification of a multivariate forecast objective, data grouping before constructing factors, and selection of the number of factors in a data-driven way. Our empirical results show that each of these features helps to improve forecast accuracy, especially for the shortest and longest maturities. The data-driven methods perform well in relatively volatile periods, when simpler models do not suffice.