Correlations
When you create a combined view, TotalKPI automatically calculates correlation coefficients between each pair of data sources. This helps you understand which metrics move together and which move in opposite directions.
What is Correlation?
Correlation measures the statistical relationship between two sets of data:
- +1.0 - perfect positive correlation (both metrics move in the same direction).
- 0.0 - no correlation (the metrics are unrelated).
- -1.0 - perfect negative correlation (when one goes up, the other goes down).
In practice, values above +0.7 or below -0.7 suggest a strong relationship worth investigating.
Reading Correlations
Each combined view card shows correlation information:
- For a view with two sources, the correlation is displayed directly.
- For a view with three or more sources, correlations for each pair are listed and can be expanded with the chevron button.
Each correlation row shows:
- The two source names being compared.
- The correlation coefficient value.
- A visual strength indicator.
Important Notes
Correlation does not imply causation. Two metrics trending together doesn't necessarily mean one causes the other - they could both be influenced by a third factor, or the relationship could be coincidental.
Correlations are most meaningful when you have a reasonable number of overlapping data points between sources. If two sources cover very different time periods, the correlation may not be reliable.