2011
DOI: 10.1016/j.ijforecast.2010.04.002
|View full text |Cite
|
Sign up to set email alerts
|

Forecasting the term structures of Treasury and corporate yields using dynamic Nelson-Siegel models

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

3
22
0
2

Year Published

2012
2012
2023
2023

Publication Types

Select...
9
1

Relationship

0
10

Authors

Journals

citations
Cited by 38 publications
(27 citation statements)
references
References 15 publications
3
22
0
2
Order By: Relevance
“…We also observe the more flexible model configurations, such as the time varying loadings and the dynamic NSS model which provides better fit in-sample, performs badly out-of-sample compared with the more parsimonious alternatives. Yu and Zivot (2010) corroborate this result using corporate bonds data. A conclusion from this analysis is that allowing for time varying loadings, in terms of forecasting, can be labelled as excessive.…”
Section: Dynamic Nelson-siegel-svensson Model (Nss)supporting
confidence: 75%
“…We also observe the more flexible model configurations, such as the time varying loadings and the dynamic NSS model which provides better fit in-sample, performs badly out-of-sample compared with the more parsimonious alternatives. Yu and Zivot (2010) corroborate this result using corporate bonds data. A conclusion from this analysis is that allowing for time varying loadings, in terms of forecasting, can be labelled as excessive.…”
Section: Dynamic Nelson-siegel-svensson Model (Nss)supporting
confidence: 75%
“…Especially for short-term investment grade bonds and long-term high-yield bonds. But the dynamics of short-term high-yield bonds varies with time, and the parameter of instability [23].…”
Section: Dr(t)=(θ-r(t))dt+√vdb(t)mentioning
confidence: 99%
“…Examples are Duffie-Kan restrictions (Duffie and Kan, 1996), smoothing restrictions (Koopman and Van der Wel, 2010) Yu and Zivot (2010) find that using the state-space estimation method results in poor out-of-sample performance compared with the two-step procedure.…”
Section: General Factor Modelmentioning
confidence: 99%