Observe the impact of model parameters
In this exercise, you will call the predefined function simulate_GARCH()
again, and study the impact of GARCH model parameters on simulated results.
Specifically, you will simulate two GARCH(1,1) time series, they have the same omega
and alpha
, but different beta
as input.
Recall in GARCH(1,1), since \(\beta\) is the coefficient of lag-1 variance, if the \(\alpha\) is fixed, the larger the \(\beta\), the longer the duration of the impact. In other words, high or low volatility periods tend to persist. Pay attention to the plotted results and see whether you can verify the \(\beta\) impact.
This exercise is part of the course
GARCH Models in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# First simulated GARCH
sim_resid, sim_variance = simulate_GARCH(n = ____, omega = ____,
alpha = ____, beta = ____)
plt.plot(sim_variance, color = 'orange', label = 'Variance')
plt.plot(sim_resid, color = 'green', label = 'Residuals')
plt.legend(loc='upper right')
plt.show()