Why Gaussian macro-finance term structure models are (nearly) unconstrained factor-VARs

Scott Joslin, Anh Tuan Le, Kenneth J. Singleton

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

This paper explores the implications of filtering and no-arbitrage for the maximum likelihood estimates of the entire conditional distribution of the risk factors and bond yields in Gaussian macro-finance term structure model (MTSM) when all yields are priced imperfectly. For typical yield curves and macro-variables studied in this literature, the estimated joint distribution within a canonical MTSM is nearly identical to the estimate from an economic-model-free factor vector-autoregression (factor-VAR), even when measurement errors are large. It follows that a canonical MTSM offers no new insights into economic questions regarding the historical distribution of the macro risk factors and yields, over and above what is learned from a factor-VAR. These results are rotation-invariant and, therefore, apply to many of the specifications in the literature.

Original languageEnglish (US)
Pages (from-to)604-622
Number of pages19
JournalJournal of Financial Economics
Volume109
Issue number3
DOIs
StatePublished - Sep 1 2013

Fingerprint

Term structure models
Factors
Finance
Risk factors
Vector autoregression
Conditional distribution
Joint distribution
Measurement error
Bond yields
Maximum likelihood
Economics
No-arbitrage
Yield curve

All Science Journal Classification (ASJC) codes

  • Accounting
  • Finance
  • Economics and Econometrics
  • Strategy and Management

Cite this

@article{00a6e44f0a6e4ba38fcd692ca87156a0,
title = "Why Gaussian macro-finance term structure models are (nearly) unconstrained factor-VARs",
abstract = "This paper explores the implications of filtering and no-arbitrage for the maximum likelihood estimates of the entire conditional distribution of the risk factors and bond yields in Gaussian macro-finance term structure model (MTSM) when all yields are priced imperfectly. For typical yield curves and macro-variables studied in this literature, the estimated joint distribution within a canonical MTSM is nearly identical to the estimate from an economic-model-free factor vector-autoregression (factor-VAR), even when measurement errors are large. It follows that a canonical MTSM offers no new insights into economic questions regarding the historical distribution of the macro risk factors and yields, over and above what is learned from a factor-VAR. These results are rotation-invariant and, therefore, apply to many of the specifications in the literature.",
author = "Scott Joslin and Le, {Anh Tuan} and Singleton, {Kenneth J.}",
year = "2013",
month = "9",
day = "1",
doi = "10.1016/j.jfineco.2013.04.004",
language = "English (US)",
volume = "109",
pages = "604--622",
journal = "Journal of Financial Economics",
issn = "0304-405X",
publisher = "Elsevier",
number = "3",

}

Why Gaussian macro-finance term structure models are (nearly) unconstrained factor-VARs. / Joslin, Scott; Le, Anh Tuan; Singleton, Kenneth J.

In: Journal of Financial Economics, Vol. 109, No. 3, 01.09.2013, p. 604-622.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Why Gaussian macro-finance term structure models are (nearly) unconstrained factor-VARs

AU - Joslin, Scott

AU - Le, Anh Tuan

AU - Singleton, Kenneth J.

PY - 2013/9/1

Y1 - 2013/9/1

N2 - This paper explores the implications of filtering and no-arbitrage for the maximum likelihood estimates of the entire conditional distribution of the risk factors and bond yields in Gaussian macro-finance term structure model (MTSM) when all yields are priced imperfectly. For typical yield curves and macro-variables studied in this literature, the estimated joint distribution within a canonical MTSM is nearly identical to the estimate from an economic-model-free factor vector-autoregression (factor-VAR), even when measurement errors are large. It follows that a canonical MTSM offers no new insights into economic questions regarding the historical distribution of the macro risk factors and yields, over and above what is learned from a factor-VAR. These results are rotation-invariant and, therefore, apply to many of the specifications in the literature.

AB - This paper explores the implications of filtering and no-arbitrage for the maximum likelihood estimates of the entire conditional distribution of the risk factors and bond yields in Gaussian macro-finance term structure model (MTSM) when all yields are priced imperfectly. For typical yield curves and macro-variables studied in this literature, the estimated joint distribution within a canonical MTSM is nearly identical to the estimate from an economic-model-free factor vector-autoregression (factor-VAR), even when measurement errors are large. It follows that a canonical MTSM offers no new insights into economic questions regarding the historical distribution of the macro risk factors and yields, over and above what is learned from a factor-VAR. These results are rotation-invariant and, therefore, apply to many of the specifications in the literature.

UR - http://www.scopus.com/inward/record.url?scp=84879797767&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879797767&partnerID=8YFLogxK

U2 - 10.1016/j.jfineco.2013.04.004

DO - 10.1016/j.jfineco.2013.04.004

M3 - Article

VL - 109

SP - 604

EP - 622

JO - Journal of Financial Economics

JF - Journal of Financial Economics

SN - 0304-405X

IS - 3

ER -