Codeless Time Series Analysis with KNIME by Corey Weisinger Maarit Widmann Daniele Tonini

Author:Corey Weisinger, Maarit Widmann, Daniele Tonini
Language: eng
Format: epub
Publisher: Packt Publishing Pvt Ltd
Published: 2022-07-25T00:00:00+00:00

Figure 7.6 – The Remove Seasonality component and configuration dialog

Set the Lag value in the configuration dialog to 1 for standard differencing or higher for seasonal differencing, as we will discuss shortly. In Figure 7.7, we can see how this differencing affects our time series and help us reach the weak stationarity requirement:

Figure 7.7 – Time series with an upward trend, corrected with standard differencing

On the left-hand side of Figure 7.7, we see a time series with a rather obvious upward trend (I’ve added this artificially for clarity). This breaks one of the requirements for weak stationarity, as the mean is clearly changing over time. Since our series is trending linearly, a single application of standard differencing was sufficient to remove the trend. If we had a quadratic trend, or something even more aggressive, an additional application of differencing would be required. In the next section, we’ll see how easy this additional application is to implement:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.