The Mode Is 37 and the Maximum Is 38
Gepubliceerd op 5-11-2026 · 3 min leestijd · Dagelijkse calculators
Lena Hoffmann — Redacteur wetenschap en onderwijs bij OneKitly
Wiskunde · Natuurkunde
Getoetst aan 2 bronnen
Take 37, 23, 37, 38, 2, 19, 21 and 29. The mean is 25.75, the median is 26, and the mode is 37 — the most frequent value, and also the second-highest in the set. Nothing has gone wrong: the mode simply reports which value repeats, and in a small sample a repeat can happen anywhere. The sample standard deviation is 12.27 and the interquartile range 16.5, both of which say the numbers are widely spread. Reporting only the mode here would suggest a typical value of 37, which six of the eight observations fall short of.
Mean 25.75, median 26, mode 37. Three summaries of the same eight numbers, pointing in three directions, and only one of them near the top of the range.
One value out of eight moves everything except one measure
Removing the single value of 2 lifts the mean by 13 %, the median by three points, and cuts the standard deviation by a third and the range by nearly half. The interquartile range barely moves, from 16.5 to 15, because it is computed from the middle half of the data and the removed point was never in it. That contrast is the whole argument for reporting a robust measure of spread alongside a conventional one: when the two disagree sharply, an extreme value is doing the disagreeing, and it is worth finding out whether it is a real observation or a typing error.
Why the standard deviation divides by seven and not eight
The figure of 12.27 uses the sample convention, dividing the summed squared deviations by one less than the count. Dividing by eight instead gives 11.48, which is smaller and, for a sample meant to represent something larger, biased low: the deviations were measured from the sample's own mean, which sits closer to the data than the true mean of the population would. Subtracting one from the divisor corrects for that. The distinction matters most in small samples — here it is 7 %, and at a hundred observations it is under 1 % — and a calculator that does not say which convention it used has left out something a reader may need.
| Measure | With the outlier | Without it |
|---|---|---|
| Mean | 25.75 | 29.14 |
| Median | 26 | 29 |
| Standard deviation | 12.27 | 8.25 |
| Range | 36 | 19 |
| Interquartile range | 16.5 | 15 |
Uitgewerkt met onze eigen calculator
Statistiekcalculator
Gegeven
- Gegevens
- 37, 24, 41, 44, 2, 24, 27, 39
Resultaat
- Aantal
- 8
- Som
- 238
- Gemiddelde
- 29,75
- Mediaan
- 32
- Minimum
- 2
- Maximum
- 44
- Bereik
- 42
- Q1
- 24
- Q3
- 39,5
- IQR
- 15,5
- Steekproefvariantie
- 187,357
- Standaarddeviatie (steekproef)
- 13,688
Deze cijfers komen uit de calculator hieronder, ze zijn niet met de hand ingetypt — ze worden opnieuw berekend telkens als de tool verandert.
Reken het door met je eigen cijfers →Veelgestelde vragen
- What if two values tie for most frequent?
- Then there are two modes, and the summary becomes a list rather than a number. Sets with several modes are common in small samples and in data that mixes two populations — a distribution of heights across a mixed group, for instance, or response times split between cached and uncached requests. A calculator forced to return one value will pick the first or the smallest, which conceals exactly the structure worth noticing. Whenever a mode is reported without saying how many there were, it is worth checking the histogram before drawing conclusions from it.
- Which average should be reported by default?
- The median, unless there is a reason to prefer the mean. The median describes the typical case and survives outliers; the mean is the right choice when totals matter — an average order value multiplied by order count must give revenue, and only the mean does that. The mode earns its place for categories rather than numbers, where 'most common' is the only sensible summary. Reporting all three costs nothing and immediately reveals whether the distribution is symmetric, which is the first thing a reader should want to know and the thing a single figure never says.
Artikelen die je misschien interesseren
Alle gidsen →Vergelijkbare tools
Bronnen
Een fout in dit artikel gezien?