haarWT: Function to apply the (univariate) Haar wavelet transform

In mvLSWimpute: Imputation Methods for Multivariate Locally Stationary Time Series

Function to apply the (univariate) Haar wavelet transform

Description

This function applies the (univariate) Haar wavelet transform. For a time series containing missing values, the wavelet coefficients are generating and any NAs remain intact.

Usage

haarWT(data)

Arguments

data	Input univariate time series.

Value

Returns a list containing the following elements:

C	Matrix containing the smooth coefficients for the transform.
D	Matrix containing the detail coefficients for the transform.

Examples

set.seed(1)
X <- matrix(rnorm(2 * 2^8), ncol = 2)
X[1:2^7, 2] <- 3 * (X[1:2^7, 2] + 0.95 * X[1:2^7, 1])
X[-(1:2^7), 2] <- X[-(1:2^7), 2] - 0.95 * X[-(1:2^7), 1]
X[-(1:2^7), 1] <- X[-(1:2^7), 1] * 4
X <- as.ts(X)

# compute the haar wavelet coefficients of the first time series component:

Xwt1 = haarWT(X[, 1])

mvLSWimpute documentation built on Aug. 16, 2022, 5:06 p.m.