scholarly journals Time-varying return predictability and adaptive markets hypothesis: Evidence on MIST countries from a novel wild bootstrap likelihood ratio approach

2020 ◽  
Vol 34 (2) ◽  
pp. 101-113
Author(s):  
Oktay Ozkan
2018 ◽  
Vol 410 (13) ◽  
pp. 3073-3091 ◽  
Author(s):  
Agnieszka Martyna ◽  
Hans-Eike Gäbler ◽  
Andreas Bahr ◽  
Grzegorz Zadora

Author(s):  
Daniele Bianchi ◽  
Matthias Büchner ◽  
Andrea Tamoni

Abstract We show that machine learning methods, in particular, extreme trees and neural networks (NNs), provide strong statistical evidence in favor of bond return predictability. NN forecasts based on macroeconomic and yield information translate into economic gains that are larger than those obtained using yields alone. Interestingly, the nature of unspanned factors changes along the yield curve: stock- and labor-market-related variables are more relevant for short-term maturities, whereas output and income variables matter more for longer maturities. Finally, NN forecasts correlate with proxies for time-varying risk aversion and uncertainty, lending support to models featuring both channels.


2017 ◽  
Vol 57 (3) ◽  
pp. 181-192 ◽  
Author(s):  
Andrew van Es ◽  
Wim Wiarda ◽  
Maarten Hordijk ◽  
Ivo Alberink ◽  
Peter Vergeer

2013 ◽  
Vol 10 (1) ◽  
pp. 34-40 ◽  
Author(s):  
Massimo Guidolin ◽  
David G. McMillan ◽  
Mark E. Wohar

Author(s):  
R. G. Keats ◽  
Winifred Frost ◽  
Annette Dobson

AbstractThe likelihood ratio approach to the detection of small signals in the presence of noise is investigated in the case where the available data have been clipped. The statistic obtained is the ratio of orthant probabilities and appears intractable; accordingly an approximation to this statistic is developed by truncating an appropriate Taylor expansion. Approximations are obtained for the mean and variance of this modified statistic and compared with those obtained from computer simulations.


Sign in / Sign up

Export Citation Format

Share Document