A median is the middle value: half the postings are below, half above. It is the right summary for salary data because it survives outliers — one absurd executive package does not drag it around the way an average would.
It is still one number describing a shape, and the shape matters.
Same median, different markets
Consider two cohorts with an identical median of $130,000:
| Cohort | 25th | Median | 75th | 90th |
|---|---|---|---|---|
| A — narrow | $122k | $130k | $139k | $148k |
| B — wide | $88k | $130k | $181k | $240k |
In A the role is standardised: seniority barely moves pay, and negotiation has little room. In B the title spans junior to staff, and your outcome depends almost entirely on which end you land in. Same median, completely different advice.
The four numbers worth reading
- 25th percentile — what the bottom of the market looks like. Below it, you are being underpaid relative to the advertised market.
- Median — the centre. A reasonable target if your experience is typical for the cohort.
- 75th percentile — reachable with strong, relevant experience.
- 90th — usually a different job wearing the same title.
Three ways a median misleads
- Selection. It covers only postings that published a range. If disclosure is 15%, the median describes those 15%.
- Level mixing. "Engineer" spans a factor of three. Split by seniority before drawing conclusions.
- Geographic mixing. A national median blends metros with very different costs. Narrow to a city.
How we present it
Every cohort page shows the histogram, the four percentiles, the split by seniority, and the disclosure rate. That is more than one number because one number would let you reach a confident wrong conclusion, and the whole point of the product is not doing that.