Application of A Quantile Regression to Estimate Across Which Quantiles the US Federal Reserve Sets the Monetary Policy In Relation to Short, Medium and Long-Term Yields of the US Interest Rates

In this article, we are investigating the effects of the macroeconomic variables. We have applied a Quantile regression, (including LAD), in EViews 6 to test the quantile of the natural logarithmic returns of the seasonally adjusted money supply, (M2) on the natural logarithmic returns of the 3-month, 5-year and 10-year Treasury with constant maturities. The aim by using this methodology is to extend the conditional mean analysis of the dependent variable in relation to the independent variables. We want to test across which quantiles the US Federal Reserve sets the monetary policy in relation to interest rates. Therefore, we use as yardstick of the quantile to estimate the value of 0.5, 0.85, 0.90 and 0.95. By using other measures of locations such as the median or the 90th, 95th percentiles of the cumulative distribution function, we are able to better describe, understand and analyse the median regression. We have found mixed results by using two methods that estimate the covariance matrix of the quantile regression. The total dataset includes 277 observations. The data that we have used are monthly returns starting from 01/01/1990 to 01/01/2013 and total to 276 observations. The data was obtained from the Federal Reserve Statistical Release Department and the symbols of the series are H.6 and H.15