Download Now Free registration required
The author optimally incorporates factors estimated from a large panel of macroeconomic time series in the estimation of two relevant signals related to real activity: business cycle fluctuations and the medium to long-run component of output growth. This latter signal conveys information on the growth of real activity but contains no high-frequency oscillations. For forecasting purposes the author shows that targeting this object can prove more useful than targeting the original (noisy) time series. In fact, with conventional models, high-frequency fluctuations are always approximated despite being (possibly) unpredictable or idiosyncratic.
- Format: PDF
- Size: 514.86 KB