Cherry-picking: base period
About this app
Drag a time window over a price series — the same stock looks "great" or "catastrophic". Toggle the index base; the sales-succession case shows how the reference period alone flips the promotion decision.
The idea
Every growth figure has a start and an end. The starting point is called the base period, and the change is measured against it, often as an index I = 100 · P(t)/P(base). Whoever chooses start and end freely can tell very different stories with the same series: starting at a low produces strong growth, starting at a peak produces a loss. The data stay correct; only the slice is chosen. You meet this kind of cherry-picking in fund brochures, annual reports and headlines.
What the app shows
At the top you see a simulated price series over five years. You drag a window across it, by the frame or by the handles. Below, the slice is enlarged and, if you like, indexed to 100 at the window start. Buttons set typical periods: 1 day, 3 months, 6 months, 1 year, 5 years and Max. A verdict sums up the window as a headline, from “Great!” through “Solid” to “Disaster!”. The “Cherry-pick” button finds a flattering window for you.
Sales mode
In “Sales” mode you see the revenue of two regions over 15 months. As base period you choose April to March, January to December or the full range. Depending on the choice, region 1 or region 2 is ahead, and with it the person who would be promoted changes. Try all three periods and ask yourself what justification you could give for each. The remedy to remember: state start, end and base, and show several time windows.
Frequently asked questions
- What is cherry-picking in statistics?
- Cherry-picking means selecting the part of the available data that supports a desired claim. With time series this often happens through the choice of start and end dates. Each number is correct, yet the overall picture is distorted.
- What is a base period?
- The base period is the time span against which a change or an index is measured. For an index, the value in the base period is set to 100 and all other values are expressed relative to it. A different base period can make a series look better or worse.
- How can I spot misleading return figures?
- Check whether start and end are stated and justified, and whether the period is unusually short or oddly chosen. Compare several time windows and make sure that series being compared share the same base. If this information is missing, be cautious.
- What can I try in this app?
- You drag a time window across a simulated price series and watch return and verdict change live. The “Cherry-pick” button searches for a flattering window. In sales mode the base period decides which of two regions comes out ahead.
Subject: Data & decisions
More from Data & decisions
- Anchoring effect
- Benford's law
- Berkson's paradox
- Cherry-picking: base period 2.0
- The three-cowboy duel (truel)
- The three-cowboy duel 2.0
- The three means
- The three means 2.0
A VisuApp by heyprof: interactive, free in your browser, no sign-up. What is a VisuApp? · All apps