Estimating the term structure with linear regressions: Getting to the roots of the problem

Adam Golinski; Peter Spencer

doi:10.1093/jjfinec/nbz031

Estimating the term structure with linear regressions: Getting to the roots of the problem

Adam Golinski, Peter Spencer

Economics

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

Abstract

Linear estimators of the affine term structure model are inconsistent since they cannot reproduce the factors used in estimation. This is a serious handicap empirically, giving a worse fit than the conventional MLE estimator that ensures
consistency. We show that a simple self-consistent estimator can be constructed using the eigenvalue decomposition of a regression estimator. The remaining parameters of the model follow analytically. The fit of this model is virtually indistinguishable from that of the MLE. We apply the method to estimate the model of the U.S. Treasury yields and a joint model of the U.S. and German yield curves.

Original language	English
Pages (from-to)	960-984
Number of pages	25
Journal	Journal of Financial Econometrics
Volume	19
Issue number	5
Early online date	3 Dec 2019
DOIs	https://doi.org/10.1093/jjfinec/nbz031
Publication status	Published - 2021

Bibliographical note

© The Author(s) 2019. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.

Access to Document

10.1093/jjfinec/nbz031

Golinski paper_190830
The Author(s) 2019. Published by Oxford University Press. All rights reserved. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.
Accepted author manuscript, 501 KB

Cite this

@article{edc8ad8af94f42e9875f3329509c2d19,

title = "Estimating the term structure with linear regressions: Getting to the roots of the problem",

abstract = "Linear estimators of the affine term structure model are inconsistent since they cannot reproduce the factors used in estimation. This is a serious handicap empirically, giving a worse fit than the conventional MLE estimator that ensuresconsistency. We show that a simple self-consistent estimator can be constructed using the eigenvalue decomposition of a regression estimator. The remaining parameters of the model follow analytically. The fit of this model is virtually indistinguishable from that of the MLE. We apply the method to estimate the model of the U.S. Treasury yields and a joint model of the U.S. and German yield curves.",

author = "Adam Golinski and Peter Spencer",

note = "{\textcopyright} The Author(s) 2019. This is an author-produced version of the published paper. Uploaded in accordance with the publisher{\textquoteright}s self-archiving policy. Further copying may not be permitted; contact the publisher for details.",

year = "2021",

doi = "10.1093/jjfinec/nbz031",

language = "English",

volume = "19",

pages = "960--984",

journal = "Journal of Financial Econometrics",

issn = "1479-8409",

publisher = "Oxford University Press",

number = "5",

}

TY - JOUR

T1 - Estimating the term structure with linear regressions: Getting to the roots of the problem

AU - Golinski, Adam

AU - Spencer, Peter

N1 - © The Author(s) 2019. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.

PY - 2021

Y1 - 2021

N2 - Linear estimators of the affine term structure model are inconsistent since they cannot reproduce the factors used in estimation. This is a serious handicap empirically, giving a worse fit than the conventional MLE estimator that ensuresconsistency. We show that a simple self-consistent estimator can be constructed using the eigenvalue decomposition of a regression estimator. The remaining parameters of the model follow analytically. The fit of this model is virtually indistinguishable from that of the MLE. We apply the method to estimate the model of the U.S. Treasury yields and a joint model of the U.S. and German yield curves.

AB - Linear estimators of the affine term structure model are inconsistent since they cannot reproduce the factors used in estimation. This is a serious handicap empirically, giving a worse fit than the conventional MLE estimator that ensuresconsistency. We show that a simple self-consistent estimator can be constructed using the eigenvalue decomposition of a regression estimator. The remaining parameters of the model follow analytically. The fit of this model is virtually indistinguishable from that of the MLE. We apply the method to estimate the model of the U.S. Treasury yields and a joint model of the U.S. and German yield curves.

U2 - 10.1093/jjfinec/nbz031

DO - 10.1093/jjfinec/nbz031

M3 - Article

SN - 1479-8409

VL - 19

SP - 960

EP - 984

JO - Journal of Financial Econometrics

JF - Journal of Financial Econometrics

IS - 5

ER -