Method
Within measurement noise
A change is within measurement noise when it is too small to distinguish from the ordinary variation of measuring the same thing twice. Zebora reports those moves as stable rather than as a rise or a fall, because calling them a trend would be reporting a wobble as a story.
Where you will see it
Change indicators have three states rather than two: up, down, and unchanged within noise. The AI-written summaries receive the same verdict, so a sub-threshold move is described as stable whatever the raw numbers say. And narrow slices such as individual tags carry too much uncertainty to support trend arrows at all, so we retired them.
Why this is a feature
Most reporting in this category rewards movement, because movement looks like insight. The cost is that clients act on noise and then lose confidence when it reverses next month. Saying nothing happened, when nothing happened, is the part of the method that makes the months where something did happen worth believing.
What no change actually looks like
Split a single month's answers into two random halves and score them separately. Nothing differs between them by construction, yet the two scores will not match — they will sit a couple of points apart, and a narrow slice will vary far more than that. Any reporting that calls a move of that size a trend is reporting the method, not the market.
Related terms
- Noise threshold — The line a move has to clear before we call it a change.
- Confidence range — Why any single figure is a band rather than a point.
- Monthly batch — The period-to-period comparison this verdict applies to.
Last reviewed . Definitions are reviewed quarterly, and whenever the underlying measurement changes.
Don't let AI decide your brand's future without you.
See exactly where you stand vs. competitors—and what to do about it.