From the course: Python for Time Series Forecasting
Join today to access over 24,800 courses taught by industry experts.
Introducing seasonal order with SARIMA model - Python Tutorial
From the course: Python for Time Series Forecasting
Introducing seasonal order with SARIMA model
- [Instructor] If we visualize the ARIMA and SARIMA model forecasts, we observe how the ARIMA model, which was the one from the previous lesson, it's flattened out into the future and doesn't follow the increasing trends of the historical data as this ARIMA model is doing. Remember that some of the assumptions such as the normality of residuals and the homoscedasticity of the residuals weren't fulfilled during the ARIMA model. In this new notebook, I introduced you to SARIMA, which is the statistical forecasting model that will help us to solve the problem by adding a new seasonal component to to the ARIMA.. Here you can see the one we had used during the lesson, and now we introduce this ARIMA with the seasonal order to control for the seasonal patterns and get a better forecast into the future. Then we will analyze if the assumptions are met by this new model. As you can see on the normality of the residuals, having a P value higher than 0.05, and for the homoscedasticity, it…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.