Quartile Calculator

Lower fence = Q1 − 1.5 × IQR: anything below this line is unusually small for your data.

Upper fence = Q3 + 1.5 × IQR: anything above it is unusually large.

The fences are screening thresholds, not verdicts — treat flagged values as questions to investigate, not data to delete.

Quartile values depend on the convention used to locate them, so this page states its method explicitly. The calculator follows the exclusive median-split approach popularized by Moore and McCabe's Introduction to the Practice of Statistics and taught in most introductory courses:

1. Sort the data and find the median (Q2).
2. Split the sorted list into a lower and an upper half. When the count is odd, the median itself belongs to neither half.
3. Q1 is the median of the lower half; Q3 is the median of the upper half.

Spreadsheet functions such as Excel's QUARTILE.INC use linear interpolation instead, so their answers can differ from these on small data sets — our percentile calculator implements that interpolating convention if you need to match spreadsheet output. Neither convention is more correct; consistency within a single analysis is what matters.

The 1.5 × IQR rule was proposed by John Tukey, the statistician who also invented the box plot. The interquartile range spans the middle 50% of the data, so it measures spread without being influenced by the extremes — unlike the standard deviation, which an outlier can inflate enough to disguise itself. Extending fences 1.5 IQR widths beyond each quartile creates a zone that, for roughly normal data, contains about 99.3% of observations. Values outside it are rare enough to deserve a closer look.

Tukey reportedly chose 1.5 because 1 was too strict and 2 too lenient. Some analysts add a second threshold at 3 × IQR, calling points beyond it extreme outliers. Because the rule is built entirely from quartiles, it keeps working on skewed data where z-score-based screening (flagging values beyond 2 or 3 standard deviations) breaks down.

Quartiles are the skeleton of the box plot: the box runs from Q1 to Q3, the line inside marks the median, and the whiskers extend to the most extreme values still inside the fences. Anything beyond the whiskers is drawn as an individual point — the same values this calculator lists as outliers.

The quartiles also reveal skew without any plotting. If Q3 − Q2 is clearly larger than Q2 − Q1, the upper quarter of the data stretches further than the lower one and the distribution leans right; the reverse pattern leans left. For the full picture including the minimum and maximum, the five number summary calculator reports all five landmarks at once, and the descriptive statistics calculator adds the mean and mode for a complete overview.

A commuter logs seven morning trips, in minutes: 22, 18, 26, 21, 58, 20, 24 — six ordinary days and one day with a road closure. The calculator proceeds like this:

1. Sort: 18, 20, 21, 22, 24, 26, 58.
2. Median (Q2): the 4th of 7 sorted values, so Q2 = 22.
3. Split, excluding the median: lower half 18, 20, 21 and upper half 24, 26, 58.
4. Quartiles: Q1 = median of the lower half = 20; Q3 = median of the upper half = 26.
5. IQR and fences: IQR = 26 − 20 = 6; lower fence = 20 − 1.5 × 6 = 11; upper fence = 26 + 1.5 × 6 = 35.
6. Outliers: only 58 falls outside the 11-to-35 window.

The payoff of quartile thinking: the mean of these trips is 27 minutes — higher than six of the seven actual commutes, thanks to the single 58-minute day. The median of 22 with an IQR of 6 describes the routine week far more honestly, and the fence calculation isolates the road-closure day instead of letting it distort the summary.