We study the forecasting performance of three alternative large scale approaches for German key macroeconomic variables using a dataset that consists of 123 variables in quarterly frequency. These three approaches handle the dimensionality problem evoked by such a large dataset by aggregating...

This paper evaluates the forecast performance of boosting, a variable selection device, and compares it with the forecast combination schemes and dynamic factor models presented in Stock and Watson (2006). Using the same data set and comparison methodology, we find that boosting is a serious...

Due to their well-known indeterminacies, factor models require identifying assumptions to guarantee unique parameter estimates. For Bayesian estimation, these identifying assumptions are usually implemented by imposing constraints on certain model parameters. This strategy, however, may result...

This paper considers factor estimation from heterogenous data, where some of the variables are noisy and only weakly informative for the factors. To identify the irrelevant variables, we search for zero rows in the loadings matrix of the factor model. To sharply separate these irrelevant...