Simplify the model with p-values
Leonardo da Vinci once said: "Simplicity is the ultimate sophistication." It also applies to data science modeling. In this exercise, you will practice using the p-values to decide the necessity of model parameters, and define a parsimonious model without insignificant parameters.
The null hypothesis is the parameter value is zero. If the p-value is larger than a given confidence level, the null hypothesis cannot be rejected, meaning the parameter is not statistically significant, hence not necessary.
A GARCH model has been defined and fitted by the Bitcoin return data. The model result is saved in gm_result.
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.
# Print model fitting summary
print(gm_result.____())
# Get parameter stats from model summary
para_summary = pd.DataFrame({'parameter':gm_result.____,
'p-value': gm_result.____})
# Print out parameter stats
print(____)