Details
| Original language | English |
|---|---|
| Article number | 106026 |
| Journal | Journal of Banking and Finance |
| Volume | 124 |
| Early online date | 10 Dec 2020 |
| Publication status | Published - Mar 2021 |
Abstract
Researchers and practitioners employ a variety of time-series processes to forecast betas, either using short-memory models or implicitly imposing infinite memory. We find that both approaches are inadequate: betas show consistent long-memory properties. For the vast majority of stocks, we reject both the short-memory and difference-stationary (random walk) alternatives. A pure long-memory model reliably provides superior beta forecasts compared to all alternatives. Accounting for long memory in beta also pays off economically for portfolio formation. We widely document the robustness of these results.
Keywords
- Beta, Forecasting, Long memory, Persistence, Predictability
ASJC Scopus subject areas
- Economics, Econometrics and Finance(all)
- Economics and Econometrics
- Economics, Econometrics and Finance(all)
- Finance
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Journal of Banking and Finance, Vol. 124, 106026, 03.2021.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - The memory of beta
AU - Becker, Janis
AU - Hollstein, Fabian
AU - Prokopczuk, Marcel
AU - Sibbertsen, Philipp
PY - 2021/3
Y1 - 2021/3
N2 - Researchers and practitioners employ a variety of time-series processes to forecast betas, either using short-memory models or implicitly imposing infinite memory. We find that both approaches are inadequate: betas show consistent long-memory properties. For the vast majority of stocks, we reject both the short-memory and difference-stationary (random walk) alternatives. A pure long-memory model reliably provides superior beta forecasts compared to all alternatives. Accounting for long memory in beta also pays off economically for portfolio formation. We widely document the robustness of these results.
AB - Researchers and practitioners employ a variety of time-series processes to forecast betas, either using short-memory models or implicitly imposing infinite memory. We find that both approaches are inadequate: betas show consistent long-memory properties. For the vast majority of stocks, we reject both the short-memory and difference-stationary (random walk) alternatives. A pure long-memory model reliably provides superior beta forecasts compared to all alternatives. Accounting for long memory in beta also pays off economically for portfolio formation. We widely document the robustness of these results.
KW - Long memory
KW - Beta
KW - Predictability
KW - Forecasting
KW - Persistence
KW - Beta
KW - Forecasting
KW - Long memory
KW - Persistence
KW - Predictability
UR - http://www.scopus.com/inward/record.url?scp=85099386903&partnerID=8YFLogxK
U2 - 10.1016/j.jbankfin.2020.106026
DO - 10.1016/j.jbankfin.2020.106026
M3 - Article
VL - 124
JO - Journal of Banking and Finance
JF - Journal of Banking and Finance
SN - 0378-4266
M1 - 106026
ER -