Drivers of Changes in the Interest Rate Environment in the United States

In this article, we investigate the contribution of the drivers of changes in the interest rate environment over time in the US economy. Principal Component Analysis (PCA) is often used in the world with interest rates. It rotates the original dataset linearly so that the modified dataset is orthogonal and better represents variation within the dataset. It has proven itself to be a powerful statistical method in the field of yield curve analysis. PCA-based time structure models usually provide an accurate fit to observed returns and explain most of fluctuations. Although the main components are the building blocks of modern time structure models, this approach has been less studied for risk modeling. Interest rate risk models are usually difficult to define and evaluate due to the changing modes of profitability and volatility. In this article, we combine estimates of conditional volatility of the main components within the framework of quantile regression (QREG) to derive estimates of the profitability of the distribution. This study will be conducted based on the historical values of the US curve, starting in 2006. Also, the decomposition of changes in yields at different durations and relative to changes in different shapes is presented.