1. Learn
    2. /
  2. Courses
    3. /
  3. GARCH Models in Python

Exercise

Compare forecast results

Different rolling window approaches can generate different forecast results. In this exercise, let's take a closer look by comparing these forecast results.

First, you will use a GARCH model to predict Bitcoin return volatility with an expanding window and a fixed rolling window approach respectively. Then you will plot both forecast results together to visualize the difference.

The Bitcoin dataset is preloaded in bitcoin_data, and feel free to explore its columns 'Close' and 'Return'. Variance forecast generated with an expanding window approach is saved in variance_expandwin, and that with a fixed rolling window approach is saved in variance_fixedwin.

Instructions 1/3

undefined XP
    1
    2
    3
  • Print out the first 5 rows of variance forecast stored in variance_expandwin and variance_fixedwin respectively.