Forecasting Based on Decomposed Financial Return Series: A Wavelet Analysis

We transform financial return series into its frequency and time domain via wavelet decomposition to separate short-run noise from long-run trends and assess the relevance of each frequency to value-at-risk (VaR) forecast. Furthermore, we analyze financial assets in calm and turmoil market times and show that daily 95% VaR forecasts are mainly driven by the volatility that is captured by the first scales comprising the short-run information, whereas more timescales are needed to adequately forecast 99% VaR. As a result, individual timescales linked via copulas outperform classical parametric VaR approaches that incorporate all information available. Copyright (c) 2015 John Wiley & Sons, Ltd.