Exchange rate predictability, risk premiums, and predictive system

Yuhyeon Bak; Cheolbeom Park

doi:10.1016/j.econmod.2022.106024

Exchange rate predictability, risk premiums, and predictive system

Yuhyeon Bak, Cheolbeom Park

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

Abstract

Uncovered interest rate parity (UIP), a basic assumption in many theoretical models, is known to perform poorly in forecasting exchange rate movements, especially in the short run. One possible reason for this failure is the existence of unobservable risk premium. We estimate the unobservable risk premium with a Bayesian approach having the risk premium as a latent variable and the implied volatility of at-the-money currency options as an imperfect predictor. We find in most cases that expected exchange rate changes, constructed from forward-spot differentials and estimated risk premiums, track actual exchange rate changes more closely than do the fitted values of the predictive regression (i.e. the Fama regression). An out-of-sample analysis reveals that adding the estimated risk premium greatly improves the short-run predictability of exchange rates in general. These findings strongly suggest that the risk premium is important in understanding the dynamics of exchange rate and the UIP puzzle.

Original language	English
Article number	106024
Journal	Economic Modelling
Volume	116
DOIs	https://doi.org/10.1016/j.econmod.2022.106024
Publication status	Published - 2022 Nov

Bibliographical note

Funding Information:
We thank the editor, Sushanta Mallick, and two anonymous reviewers for their valuable comments and suggestions. Bak acknowledges that this work was supported by the National Research Foundation of Korea ( NRF ) grant funded by the Korean government ( MSIT ) ( 2020R1G1A1005045 ) and the AIIP ( 1.220045.01 ) grant funded by UNIST . Park acknowledges that this work was supported by Korea University Grant ( K1801831 ). All errors are our own.

Funding Information:
We thank the editor, Sushanta Mallick, and two anonymous reviewers for their valuable comments and suggestions. Bak acknowledges that this work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (2020R1G1A1005045) and the AIIP (1.220045.01) grant funded by UNIST. Park acknowledges that this work was supported by Korea University Grant (K1801831). All errors are our own.Funding sources are National Research Foundation Korea (MSIT), South Korea; UNIST, South Korea; Korea University, South Korea. Federal fund rates are variable name in the data and has nothing to do with funding sources.

Publisher Copyright:
© 2022 Elsevier B.V.

Keywords

Bayesian approach
Exchange rate
Predictive system
Risk premium

ASJC Scopus subject areas

Economics and Econometrics

Access to Document

10.1016/j.econmod.2022.106024

Cite this

@article{75cec9d5633241d7a8c9108464fbfc0e,

title = "Exchange rate predictability, risk premiums, and predictive system",

abstract = "Uncovered interest rate parity (UIP), a basic assumption in many theoretical models, is known to perform poorly in forecasting exchange rate movements, especially in the short run. One possible reason for this failure is the existence of unobservable risk premium. We estimate the unobservable risk premium with a Bayesian approach having the risk premium as a latent variable and the implied volatility of at-the-money currency options as an imperfect predictor. We find in most cases that expected exchange rate changes, constructed from forward-spot differentials and estimated risk premiums, track actual exchange rate changes more closely than do the fitted values of the predictive regression (i.e. the Fama regression). An out-of-sample analysis reveals that adding the estimated risk premium greatly improves the short-run predictability of exchange rates in general. These findings strongly suggest that the risk premium is important in understanding the dynamics of exchange rate and the UIP puzzle.",

keywords = "Bayesian approach, Exchange rate, Predictive system, Risk premium",

author = "Yuhyeon Bak and Cheolbeom Park",

note = "Funding Information: We thank the editor, Sushanta Mallick, and two anonymous reviewers for their valuable comments and suggestions. Bak acknowledges that this work was supported by the National Research Foundation of Korea ( NRF ) grant funded by the Korean government ( MSIT ) ( 2020R1G1A1005045 ) and the AIIP ( 1.220045.01 ) grant funded by UNIST . Park acknowledges that this work was supported by Korea University Grant ( K1801831 ). All errors are our own. Funding Information: We thank the editor, Sushanta Mallick, and two anonymous reviewers for their valuable comments and suggestions. Bak acknowledges that this work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (2020R1G1A1005045) and the AIIP (1.220045.01) grant funded by UNIST. Park acknowledges that this work was supported by Korea University Grant (K1801831). All errors are our own.Funding sources are National Research Foundation Korea (MSIT), South Korea; UNIST, South Korea; Korea University, South Korea. Federal fund rates are variable name in the data and has nothing to do with funding sources. Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.",

year = "2022",

month = nov,

doi = "10.1016/j.econmod.2022.106024",

language = "English",

volume = "116",

journal = "Economic Modelling",

issn = "0264-9993",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Exchange rate predictability, risk premiums, and predictive system

AU - Bak, Yuhyeon

AU - Park, Cheolbeom

N1 - Funding Information: We thank the editor, Sushanta Mallick, and two anonymous reviewers for their valuable comments and suggestions. Bak acknowledges that this work was supported by the National Research Foundation of Korea ( NRF ) grant funded by the Korean government ( MSIT ) ( 2020R1G1A1005045 ) and the AIIP ( 1.220045.01 ) grant funded by UNIST . Park acknowledges that this work was supported by Korea University Grant ( K1801831 ). All errors are our own. Funding Information: We thank the editor, Sushanta Mallick, and two anonymous reviewers for their valuable comments and suggestions. Bak acknowledges that this work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (2020R1G1A1005045) and the AIIP (1.220045.01) grant funded by UNIST. Park acknowledges that this work was supported by Korea University Grant (K1801831). All errors are our own.Funding sources are National Research Foundation Korea (MSIT), South Korea; UNIST, South Korea; Korea University, South Korea. Federal fund rates are variable name in the data and has nothing to do with funding sources. Publisher Copyright: © 2022 Elsevier B.V.

PY - 2022/11

Y1 - 2022/11

N2 - Uncovered interest rate parity (UIP), a basic assumption in many theoretical models, is known to perform poorly in forecasting exchange rate movements, especially in the short run. One possible reason for this failure is the existence of unobservable risk premium. We estimate the unobservable risk premium with a Bayesian approach having the risk premium as a latent variable and the implied volatility of at-the-money currency options as an imperfect predictor. We find in most cases that expected exchange rate changes, constructed from forward-spot differentials and estimated risk premiums, track actual exchange rate changes more closely than do the fitted values of the predictive regression (i.e. the Fama regression). An out-of-sample analysis reveals that adding the estimated risk premium greatly improves the short-run predictability of exchange rates in general. These findings strongly suggest that the risk premium is important in understanding the dynamics of exchange rate and the UIP puzzle.

AB - Uncovered interest rate parity (UIP), a basic assumption in many theoretical models, is known to perform poorly in forecasting exchange rate movements, especially in the short run. One possible reason for this failure is the existence of unobservable risk premium. We estimate the unobservable risk premium with a Bayesian approach having the risk premium as a latent variable and the implied volatility of at-the-money currency options as an imperfect predictor. We find in most cases that expected exchange rate changes, constructed from forward-spot differentials and estimated risk premiums, track actual exchange rate changes more closely than do the fitted values of the predictive regression (i.e. the Fama regression). An out-of-sample analysis reveals that adding the estimated risk premium greatly improves the short-run predictability of exchange rates in general. These findings strongly suggest that the risk premium is important in understanding the dynamics of exchange rate and the UIP puzzle.

KW - Bayesian approach

KW - Exchange rate

KW - Predictive system

KW - Risk premium

UR - http://www.scopus.com/inward/record.url?scp=85137390749&partnerID=8YFLogxK

U2 - 10.1016/j.econmod.2022.106024

DO - 10.1016/j.econmod.2022.106024

M3 - Article

AN - SCOPUS:85137390749

SN - 0264-9993

VL - 116

JO - Economic Modelling

JF - Economic Modelling

M1 - 106024

ER -

Exchange rate predictability, risk premiums, and predictive system

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this