Department of Economics and Business Economics

Using the entire yield curve in forecasting output and inflation

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Standard

Using the entire yield curve in forecasting output and inflation. / Hillebrand, Eric; Huang, Huiyu; Lee, Tae Hwy; Li, Canlin.

In: Econometrics, Vol. 6, No. 3, 40, 01.09.2018.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Harvard

APA

CBE

MLA

Vancouver

Author

Hillebrand, Eric ; Huang, Huiyu ; Lee, Tae Hwy ; Li, Canlin. / Using the entire yield curve in forecasting output and inflation. In: Econometrics. 2018 ; Vol. 6, No. 3.

Bibtex

@article{b57e106da51945c7958c3b4513918ac6,
title = "Using the entire yield curve in forecasting output and inflation",
abstract = "In forecasting a variable (forecast target) using many predictors, a factor model with principal components (PC) is often used. When the predictors are the yield curve (a set of many yields), the Nelson–Siegel (NS) factor model is used in place of the PC factors. These PC or NS factors are combining information (CI) in the predictors (yields). However, these CI factors are not “supervised” for a specific forecast target in that they are constructed by using only the predictors but not using a particular forecast target. In order to “supervise” factors for a forecast target, we follow Chan et al. (1999) and Stock and Watson (2004) to compute PC or NS factors of many forecasts (not of the predictors), with each of the many forecasts being computed using one predictor at a time. These PC or NS factors of forecasts are combining forecasts (CF). The CF factors are supervised for a specific forecast target. We demonstrate the advantage of the supervised CF factor models over the unsupervised CI factor models via simple numerical examples and Monte Carlo simulation. In out-of-sample forecasting of monthly US output growth and inflation, it is found that the CF factor models outperform the CI factor models especially at longer forecast horizons.",
keywords = "And curvature of the yield curve, Combining forecasts, Level, Nelson-Siegel factors, Principal components, Slope, Supervised factor models",
author = "Eric Hillebrand and Huiyu Huang and Lee, {Tae Hwy} and Canlin Li",
year = "2018",
month = sep,
day = "1",
doi = "10.3390/econometrics6030040",
language = "English",
volume = "6",
journal = "Econometrics",
issn = "2225-1146",
publisher = "MDPI AG",
number = "3",

}

RIS

TY - JOUR

T1 - Using the entire yield curve in forecasting output and inflation

AU - Hillebrand, Eric

AU - Huang, Huiyu

AU - Lee, Tae Hwy

AU - Li, Canlin

PY - 2018/9/1

Y1 - 2018/9/1

N2 - In forecasting a variable (forecast target) using many predictors, a factor model with principal components (PC) is often used. When the predictors are the yield curve (a set of many yields), the Nelson–Siegel (NS) factor model is used in place of the PC factors. These PC or NS factors are combining information (CI) in the predictors (yields). However, these CI factors are not “supervised” for a specific forecast target in that they are constructed by using only the predictors but not using a particular forecast target. In order to “supervise” factors for a forecast target, we follow Chan et al. (1999) and Stock and Watson (2004) to compute PC or NS factors of many forecasts (not of the predictors), with each of the many forecasts being computed using one predictor at a time. These PC or NS factors of forecasts are combining forecasts (CF). The CF factors are supervised for a specific forecast target. We demonstrate the advantage of the supervised CF factor models over the unsupervised CI factor models via simple numerical examples and Monte Carlo simulation. In out-of-sample forecasting of monthly US output growth and inflation, it is found that the CF factor models outperform the CI factor models especially at longer forecast horizons.

AB - In forecasting a variable (forecast target) using many predictors, a factor model with principal components (PC) is often used. When the predictors are the yield curve (a set of many yields), the Nelson–Siegel (NS) factor model is used in place of the PC factors. These PC or NS factors are combining information (CI) in the predictors (yields). However, these CI factors are not “supervised” for a specific forecast target in that they are constructed by using only the predictors but not using a particular forecast target. In order to “supervise” factors for a forecast target, we follow Chan et al. (1999) and Stock and Watson (2004) to compute PC or NS factors of many forecasts (not of the predictors), with each of the many forecasts being computed using one predictor at a time. These PC or NS factors of forecasts are combining forecasts (CF). The CF factors are supervised for a specific forecast target. We demonstrate the advantage of the supervised CF factor models over the unsupervised CI factor models via simple numerical examples and Monte Carlo simulation. In out-of-sample forecasting of monthly US output growth and inflation, it is found that the CF factor models outperform the CI factor models especially at longer forecast horizons.

KW - And curvature of the yield curve

KW - Combining forecasts

KW - Level

KW - Nelson-Siegel factors

KW - Principal components

KW - Slope

KW - Supervised factor models

UR - http://www.scopus.com/inward/record.url?scp=85056777432&partnerID=8YFLogxK

U2 - 10.3390/econometrics6030040

DO - 10.3390/econometrics6030040

M3 - Journal article

AN - SCOPUS:85056777432

VL - 6

JO - Econometrics

JF - Econometrics

SN - 2225-1146

IS - 3

M1 - 40

ER -