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

Exercise

Diagnostics

You have arrived at the model diagnostic stage. So far you have found that the initial time series was stationary, but may have one outlying point. You identified promising model orders using the ACF and PACF and confirmed these insights by training a lot of models and using the AIC and BIC.

You found that the ARMA(1,2) model was the best fit to our data and now you want to check over the predictions it makes before you would move it into production.

The time series savings has been loaded and the ARIMA class has been imported into your environment.

Instructions

100 XP
  • Retrain the ARMA(1,2) model on the time series, setting the trend to constant.
  • Create the 4 standard diagnostics plots.
  • Print the model residual summary statistics.