Showing 1 - 10 of 69
Previous findings indicate that the inclusion of dynamic factors obtained from a large set of predictors can improve macroeconomic forecasts. In this paper, we explore three possible further developments: (i) using automatic criteria for choosing those factors which have the greatest predictive...
Persistent link: https://www.econbiz.de/10012160746
Persistent link: https://www.econbiz.de/10012305515
Persistent link: https://www.econbiz.de/10012317696
Persistent link: https://www.econbiz.de/10014465155
Persistent link: https://www.econbiz.de/10012597684
Persistent link: https://www.econbiz.de/10014253284
We introduce the technique of band spectral panel regression (BSPR) to analyze global linkages across sectors and frequency bands. It relies on decomposing time series —allowably measured in mixed observation frequency— into “deviation cycle” dynamics by frequency band. We use it to...
Persistent link: https://www.econbiz.de/10014485646
Persistent link: https://www.econbiz.de/10013438380
component analysis (SPCA), coupled with a variety of other factor estimation as well as data shrinkage methods, including … nonlinear methods, and that using a combination of factor and other shrinkage methods often yields superior predictions. For … forms of shrinkage. For example, SPCA yields MSFE-best prediction models in many cases, particularly when coupled with …
Persistent link: https://www.econbiz.de/10009766687
This paper proposes new ℓ1-penalized quantile regression estimators for panel data, which explicitly allows for individual heterogeneity associated with covariates. We conduct Monte Carlo simulations to assess the small sample performance of the new estimators and provide comparisons of new...
Persistent link: https://www.econbiz.de/10010238040