Nelson-Siegel Model and Multicollinearity
Numerous researchers are aware of the potential multicollinearity in the Nelson-Siegel model that can lead to unstable estimations and signs contrary to expectations if the model is estimated by ordinary least squares (OLS). It is an important question to consider because the Nelson-Siegel model is used for important decision making in monetary policy (predict the capital required by Basel due to interest rate risk, decide whether to invest in certain financial products at both the individual and company levels, and make changes in monetary policy, among others). Some authors have proposed fixing the shape parameter to avoid multicollinearity problems, but that change can lead to extremely smooth time series. On the other hand, other authors have proposed estimating the Nelson-Siegel model with the ridge regression that is traditionally applied to estimate models with collinearity as an alternative to OLS. For a correct application of the ridge regression, data should be standardized, and the condition number (traditionally applied to diagnose multicollinearity) should be calculated for unit-length data. In this paper, we extend the methodology by considering the mentioned limitations. In addition, we propose an alternative methodology to allow the shape parameter to be completely free and that can be implemented with the ridge and the raise regression. This last methodology mitigates multicollinearity while maintaining the global characteristics of the original model. The contribution of this paper is illustrated with two different empirical examples for American and European treasuries. In both cases, the raise regression provides a better result than the ridge regression, mitigating the multicollinearity without fixing the shape parameter λ and obtaining a higher coefficient of determination
Year of publication: |
2022
|
---|---|
Authors: | Rodríguez Sánchez, Ainara ; garcia, catalina ; Gómez, Román Salmerón |
Publisher: |
[S.l.] : SSRN |
Saved in:
freely available
Saved in favorites
Similar items by person
-
The raise method. An alternative procedure to estimate the parameters in presence of collinearity
Garcia, Catalina, (2011)
-
Gómez, Román Salmerón, (2017)
-
Gómez, Román Salmerón, (2017)
- More ...