Conditional variance of a GARCH(1,1) model

variance(t) = omega + alpha * e(t-1)^2 + beta * variance(t-1), started at start. Each day's variance depends only on the days before it, so it is the variance the model expects for that day.

Usage

garch_variance(e, omega, alpha, beta, start)

Arguments

e

Numeric vector of the returns minus their mean.

omega, alpha, beta

The parameters of the model.

start

The variance of the first day.

Value

A numeric vector of variances, as long as e.

Examples

golemcrypto:::garch_variance(c(1, -2, 0.5, 3), omega = 0.1, alpha = 0.1, beta = 0.8, start = 2)
#> [1] 2.000 1.800 1.940 1.677