Multi-scale tests for serial correlation

Multivariate Wavelet Whittle Estimation in Long‐range Dependence

“…Estimation based on Haar wavelet indeed gives better results, possibly better than Fourier (e.g. Gencay and Signori, , in the case of tests of serial correlation). As explained earlier, a lower number of vanishing moments improves the quality of the wavelet‐based estimators (see Faÿ et al ., , in the univariate case).…”

Tests for serial correlation of unknown form in dynamic least squares regression with wavelets

“…Our modified tests are robust to models with conditionally heteroscedastic errors of unknown form. Inheriting the test design of Gençay and Signori (2015) by using the additive variance decomposition of the wavelet and the scaling coefficients, instead of any nonparametric estimation of the underlying spectrum, our test statistics converge to the normal distribution at the parametric rate under the null hypothesis (faster than the nonparametric test) and display higher power than the parametric test. In addition, contrary to the sensitiveness of finite sample performance to the choice of lag length for the parametric test, and the choice of bandwidth for the nonparametric test, our tests are rather stable when different wavelet decomposition levels are utilized.…”

Multivariate EMD-Based Modeling and Forecasting of Crude Oil Price

“…Benhmad [16] analyze the cyclical co-movement between crude oil prices and US Gross Domestic Product (GDP) using the wavelet analysis and the Granger causality test and found the existence of a cyclical relationship in the multiscale domain [16]. By decomposing the variance iteratively in different scales like low-frequency and high-frequency, Gençay [17] proposes multiscale tests of serial correlation with the improved performance [17]. Fernandez-Macho [18] examines the wavelet correlation and cross-correlation between different financial variables in the Euro stock market by using multiscale models [18].…”