spec_block_cv: Block-wise cross-validation to select the spectrum-wise...

In HaotianXu/rcov: Robust Autocovariance Matrix Estimation

Block-wise cross-validation to select the spectrum-wise robustification parameter tau for autocovariance

Description

As the title

Usage

spec_block_cv(X, S, h, lag, tau.vec, ...)

Arguments

X	A pxn matrix of observated multivariate time series.
S	A strictly positive integer corresponding to the chosen number of non-overlapping blocks.
h	A strictly positive integer corresponding to how many neighboring blocks will be removed.
lag	A strictly non-negative integer corresponding to the lag of the autocovariance.
tau.vec	A numeric vector of candidate robustification parameters (positive values).
...	Additional arguments.

Value

A numeric vector of cross validation errors (in l2 norm), corresponding to the tau.vec.

Author(s)

Haotian Xu and Stephane Guerrier

Examples

n = 100
p = 50
Sigma = diag(1, p)
set.seed(123)
X = VAR1_simu(n = n, mu = rep(0, p), skip = 300, Sigma.mat = Sigma, rho = 0.7, err.dist = "pareto")
tau.vec = seq(from = 10, to = 100, length.out = 10)
spec_block_cv(X, S = 10, h = 1, lag = 1, tau.vec)

HaotianXu/rcov documentation built on May 14, 2023, 5:04 a.m.