expweightcov: Computes the empirical exponentially weighted covariance...

In gregorkastner/factorstochvol: Bayesian Estimation of (Sparse) Latent Factor Stochastic Volatility Models

Computes the empirical exponentially weighted covariance matrix

Description

A common way to get estimates for time-varying covariance matrices is the compute the exponentially weighted empirical covariance matrix.

Usage

expweightcov(dat, alpha = 4/126, hist = 180)

Arguments

dat	Matrix containing the data, with n rows (points in time) and m columns (component series).
alpha	Speed of decay.
hist	How far to go back in time?

Value

A m times m covariance matrix estimate.

gregorkastner/factorstochvol documentation built on Dec. 11, 2023, 9:17 p.m.