Comparison of EMD and HP Filter for Cycle Extraction with Korean Macroeconomic Indices

We introduce the empirical model decomposition (EMD) to decompose a time series into a set of components in the time-frequency domain. By using EMD, we also extract cycle and trend components from major Korean macroeconomic indices and forecast the indices with the components combined. In order to evaluate their e.ciencies, we investigate volatility, autocorrelation, persistence, Granger causality, nonstationarity, and forecasting performance. They are then compared with those by Hodrick-Prescott .lter which is the most commonly used method.