Estimation
In the last exercise, the ACF and PACF were a little inconclusive. The results suggest your data could be an ARMA(p,q) model or could be an imperfect AR(3) model. In this exercise you will search over models over some model orders to find the best one according to AIC.
The time series savings has been loaded and the ARIMA class has been imported into your environment.
This exercise is part of the course
ARIMA Models in Python
Exercise instructions
- Loop over values of
pfrom 0 to 3 and values ofqfrom 0 to 3. - Inside the loop, create an ARMA(p,q) model.
- Then fit the model to the time series
savings. - At the end of each loop print the values of
pandqand the AIC and BIC.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Loop over p values from 0-3
for p in ____:
# Loop over q values from 0-3
for q in ____:
try:
# Create and fit ARMA(p,q) model
model = ____(____, order=____)
results = ____
# Print p, q, AIC, BIC
print(____)
except:
print(p, q, None, None)