The mean is a fair summary only when nothing in the data is extreme.
You are quoting for next month and want to know what a typical job is worth. Put the average of the five invoices in B7, then look at how it compares to the invoices themselves.
Solve it on your own to keep the bonus. Each hint gets one step closer to the formula.
The same formula in the other shapes it takes at work.
The mean is a fair summary only when nothing in the data is extreme.
Take out the two extremes before averaging, the way judging panels do.
The typical value for one group, ignoring the small cases.
This is the grid you start with. Cell references in the task — B6, C2 — point at the row numbers and column letters below.
| A | B | |
|---|---|---|
| 1 | Job | Invoiced |
| 2 | Logo refresh | 450 |
| 3 | Brochure | 520 |
| 4 | Website copy | 480 |
| 5 | Packaging | 610 |
| 6 | Rebrand programme | 8400 |
| 7 | Average |
The average job is worth 2092, and four of the five jobs came in under 620. A single rebrand programme has dragged the mean past almost every real invoice, so quoting it would be indefensible. This is the failure the rest of this track exists to fix: MEDIAN, a few exercises from here, is what you reach for when one value is doing this.