A Noisy Principal Component Analysis for Forward Rate Curves

TL;DR

This paper proposes a modified PCA method using long-run covariance matrices to better estimate the true volatility structure of forward rate curves affected by market microstructure noise and interpolation errors.

Contribution

It introduces a PCA approach based on long-run covariance matrices that effectively accounts for observational errors in forward rate data.

Findings

Long-run covariance PCA better captures true covariance structure.

Significant reduction in pricing errors with noisy forward rate data.

Method improves estimation accuracy in the presence of market microstructure noise.

Abstract

Principal Component Analysis (PCA) is the most common nonparametric method for estimating the volatility structure of Gaussian interest rate models. One major difficulty in the estimation of these models is the fact that forward rate curves are not directly observable from the market so that non-trivial observational errors arise in any statistical analysis. In this work, we point out that the classical PCA analysis is not suitable for estimating factors of forward rate curves due to the presence of measurement errors induced by market microstructure effects and numerical interpolation. Our analysis indicates that the PCA based on the long-run covariance matrix is capable to extract the true covariance structure of the forward rate curves in the presence of observational errors. Moreover, it provides a significant reduction in the pricing errors due to noisy data typically founded in forward rate curves.