From the course: Power BI: Integrating AI
Join today to access over 24,800 courses taught by industry experts.
Contextualizing outliers versus anomalies - Power BI Tutorial
From the course: Power BI: Integrating AI
Contextualizing outliers versus anomalies
- [Instructor] Once we detrend our actual data for seasonality and overall trends, we're left with anomalies that don't otherwise follow prescriptive time series trends. In our time series decomposition, let's start by calculating a new measure called Anomalies. We'll set it equal to the Actuals measure, and then we'll subtract the Seasonality from that and the Trend measure as well. Let's then remove the Differentials measure from our line chart. When we add our new anomalies measure to the visual, we see the line series appears well below the X-axis. We see anomalies have values in the negative seventies, for example. This is because we're subtracting the aggregated temperatures from the actual measures twice, once in the seasonality and once in the trend. So instead, we want to add the average measure back across all the selected time periods in our measure results. Because subtracting a negative value is the same as adding a positive one, let's put parentheses around the trend…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
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.