Skill · Research & Analysis
Statistics Explainer
Checks a statistical claim or chart against the traps that most often mislead, recalculates it, and rewrites it in one honest sentence.
When to use
- A headline, pitch deck, vendor report or internal dashboard makes a numerical claim you want to check.
- You have to present or rely on an analysis and want its weak points found first.
- You don't know what a statistic (p-value, odds ratio, relative risk, confidence interval) means in context.
When not to use
- You need a new analysis run on raw data. Do the analysis first (spreadsheet or code), then review it here.
- You have a whole paper to assess. The Research Paper Digest skill in this pack covers design, conflicts of interest and evidence grading in more depth.
Example
User: An ad says "Users of our app were 50% more likely to hit their savings goal!" The small print: a survey of 400 app users, 30% hit their goal, against 20% of "average savers" from a national survey.
Result (illustrative; your model's wording will differ):
Decode: measured: self-reported goal achievement. Population: 400 current app users, compared with a separate national survey. Literally says: 30% against 20%. Claimed to mean: the app makes people save better.
Missing: how the 400 users were chosen; whether both surveys asked the same question.
| Trap | Verdict | Evidence |
|---|---|---|
| Selection bias | Present | People who download a savings app are likely to be motivated savers already |
| Survivorship bias | Likely | Only current users were surveyed; people who gave up are missing |
| Confounding / cause | Present | No before-and-after or randomised comparison |
| Relative vs absolute | Present | "50% more" is 10 percentage points |
Checked and absent: chart axis (no chart).
Recalculation: 30 ÷ 20 = 1.5, so "50% more likely" (relative); the absolute gap is 30 − 20 = 10 percentage points (calculated).
What the data supports: current users report reaching their goal more often than savers in general; it does not show the app caused it.
Honest version: "In our survey of 400 current users, 30% said they reached their savings goal, compared with 20% of savers in a national survey; the two groups differ in ways that may explain the gap."
What is inside
The full skill has these sections. The ones marked “in the pack” come with the download.
- When to use on this page
- When not to use on this page
- Inputs to ask for in the pack
- Workflow in the pack
- Output format in the pack
- Example on this page
- Model notes (Oct 2026) in the pack
- Troubleshooting in the pack
Get Statistics Explainer
The full skill is a SKILL.md folder you install once and reuse: the workflow, the checklist and the answer format written out, with notes for each model. It comes in the Research & Analysis pack (3 prompts · 15 skills · 2 free), with a QUICKSTART, setup notes in every item and 12 months of updates.
All-Access 39 € vs 7 packs × 12 € = 84 € · less than buying 4 or more packs one by one
Stuck? Email support@meevra.com — we'll help you set it up.