80 Pages Posted: 5 Dec 2012 Last revised: 6 Oct 2016
Date Written: February 25, 2016
We introduce a new stylized fact: the hump-shaped behavior of slopes and coefficients of determination as a function of the aggregation horizon when running (forward/backward) predictive regressions of future excess market returns onto past economic uncertainty. To justify this finding formally, we propose a novel framework in which predictability is a property of low-frequency components of both excess market returns and economic uncertainty. We show that predictability on these low-frequency components (i.e., scale-specific predictability) translates theoretically into hump-shaped patterns of slopes and coefficients of determination upon forward/backward regressions on the raw series. If past long-run uncertainty predicts future long-run returns, it also has to predict future long-run dividend growth. We report that it does so strongly.
Keywords: long run, predictability, aggregation, risk-return trade-off
JEL Classification: C51, E32, G12, G17
Suggested Citation: Suggested Citation
Bandi, Federico M. and Perron, Benoit and Tamoni, Andrea and Tebaldi, Claudio, The Scale of Predictability (February 25, 2016). Available at SSRN: https://ssrn.com/abstract=2184260 or http://dx.doi.org/10.2139/ssrn.2184260