Predicting bond return predictability

Daniel Borup Andersen; Jonas Nygaard Eriksen; Mads Markvart Kjær; Martin Thyrsgaard

doi:10.1287/mnsc.2023.4713

Predicting bond return predictability

Daniel Borup Andersen^*, Jonas Nygaard Eriksen, Mads Markvart Kjær, Martin Thyrsgaard

^*Corresponding author for this work

Department of Economics and Business Economics

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

Abstract

This paper provides empirical evidence on predictable time variations in out-of-sample bond return predictability. Bond return predictability is associated with periods of high (low) economic activity (uncertainty), which implies that violations of the expectations hypothesis are state- dependent and linked to features of the business cycle. These state-dependencies in predictability, established by introducing a new multivariate test for equal conditional predictive ability, can be used in real-time to improve out-of-sample bond risk premia estimates and investors’ economic utility through a novel dynamic forecast combination scheme that uses predicted forecasting performance to identify the best set of methods to include in the combined forecast. Dynamically combined forecasts exhibit strong countercyclical behavior and peak during recessions.

Original language	English
Journal	Management Science
Volume	70
Issue	2
Pages (from-to)	931-951
Number of pages	21
ISSN	0025-1909
DOIs	https://doi.org/10.1287/mnsc.2023.4713
Publication status	Published - Feb 2024

Keywords

bond excess returns
equal conditional predictive ability
forecast combination
multivariate test
state dependencies

Access to Document

10.1287/mnsc.2023.4713

Cite this

@article{1f903bc0bcae4fac926b1d5a4aec21a9,

title = "Predicting bond return predictability",

abstract = "This paper provides empirical evidence on predictable time variations in out-of-sample bond return predictability. Bond return predictability is associated with periods of high (low) economic activity (uncertainty), which implies that violations of the expectations hypothesis are state- dependent and linked to features of the business cycle. These state-dependencies in predictability, established by introducing a new multivariate test for equal conditional predictive ability, can be used in real-time to improve out-of-sample bond risk premia estimates and investors{\textquoteright} economic utility through a novel dynamic forecast combination scheme that uses predicted forecasting performance to identify the best set of methods to include in the combined forecast. Dynamically combined forecasts exhibit strong countercyclical behavior and peak during recessions.",

keywords = "bond excess returns, equal conditional predictive ability, forecast combination, multivariate test, state dependencies",

author = "Andersen, {Daniel Borup} and Eriksen, {Jonas Nygaard} and Kj{\ae}r, {Mads Markvart} and Martin Thyrsgaard",

year = "2024",

month = feb,

doi = "10.1287/mnsc.2023.4713",

language = "English",

volume = "70",

pages = "931--951",

journal = "Management Science",

issn = "0025-1909",

publisher = "Institute for Operations Research and the Management Sciences (I N F O R M S)",

number = "2",

}

TY - JOUR

T1 - Predicting bond return predictability

AU - Andersen, Daniel Borup

AU - Eriksen, Jonas Nygaard

AU - Kjær, Mads Markvart

AU - Thyrsgaard, Martin

PY - 2024/2

Y1 - 2024/2

N2 - This paper provides empirical evidence on predictable time variations in out-of-sample bond return predictability. Bond return predictability is associated with periods of high (low) economic activity (uncertainty), which implies that violations of the expectations hypothesis are state- dependent and linked to features of the business cycle. These state-dependencies in predictability, established by introducing a new multivariate test for equal conditional predictive ability, can be used in real-time to improve out-of-sample bond risk premia estimates and investors’ economic utility through a novel dynamic forecast combination scheme that uses predicted forecasting performance to identify the best set of methods to include in the combined forecast. Dynamically combined forecasts exhibit strong countercyclical behavior and peak during recessions.

AB - This paper provides empirical evidence on predictable time variations in out-of-sample bond return predictability. Bond return predictability is associated with periods of high (low) economic activity (uncertainty), which implies that violations of the expectations hypothesis are state- dependent and linked to features of the business cycle. These state-dependencies in predictability, established by introducing a new multivariate test for equal conditional predictive ability, can be used in real-time to improve out-of-sample bond risk premia estimates and investors’ economic utility through a novel dynamic forecast combination scheme that uses predicted forecasting performance to identify the best set of methods to include in the combined forecast. Dynamically combined forecasts exhibit strong countercyclical behavior and peak during recessions.

KW - bond excess returns

KW - equal conditional predictive ability

KW - forecast combination

KW - multivariate test

KW - state dependencies

U2 - 10.1287/mnsc.2023.4713

DO - 10.1287/mnsc.2023.4713

M3 - Journal article

SN - 0025-1909

VL - 70

SP - 931

EP - 951

JO - Management Science

JF - Management Science

IS - 2

ER -

Predicting bond return predictability

Abstract

Keywords

Access to Document

Fingerprint

Cite this