QUARTILE Function (Gnumeric)

Quartiles describe how a sample is spread out. Q1 is the inclusive 25th percentile, Q2 the median, and Q3 the 75th percentile. The interquartile range (IQR) is Q3−Q1, measuring the width of the middle part of the distribution. Quartiles are useful for comparing store-delivery times, transaction sizes and processing queues, especially when one extreme observation would skew an average. They do not, by themselves, establish a causal explanation or a service guarantee.

Exact Gnumeric syntax

=QUARTILE(array,quart)

• array (required) — numeric sample/range, e.g. B2:B9. Use number-formatted input cells; precise Gnumeric handling of every mix of text, blanks and spreadsheet error values was not natively tested.
• quart (required) — quartile selector. Valid values are 0, 1, 2, 3, 4. The official manual documents truncation of noninteger selectors, so 2.8 is treated as 2. No default selector is documented.

The official guide says an empty array or a selector below 0 or above 4 returns #NUM!. Its public catalogue classifies QUARTILE Complete / Basic, meaning implementation complete with basic project test coverage—not native validation of this tutorial. Gnumeric QUARTILE manual; function catalogue.

Enter the following as numeric processing minutes; do not include the unit inside the cell contents.

On a narrow screen, scroll this table sideways to see every column.

Place the following formulas in D2:D9 or another unused column; keep the dataset fixed in B2:B9.

On a narrow screen, scroll this table sideways to see every column.

*Outputs are independent expected arithmetic results, not Gnumeric observations. The noninteger-selector output additionally depends on the documented Gnumeric truncation rule and still needs native testing.

Why Q3 can be 50 when no observation equals 50

The ordered observations are 5, 10, 20, 25, 31, 40, 80, 100. Gnumeric’s QUARTILE uses Hyndman–Fan method 7, which positions the pth inclusive percentile at the one-based index h=1+(n−1)×p. For Q3, p=0.75 and n=8, so h=6.25. The sixth observation is 40 and seventh is 80, giving 40+0.25×(80−40)=50. For Q1, the index is 2.75, giving 10+0.75×(20−10)=17.5. Q2 is 28, the mean of 25 and 31. Gnumeric Statistics manual — QUARTILE.

Flag candidates beyond a 1.5×IQR upper fence. The sample IQR is 50−17.5=32.5 and upper fence is 50+1.5×32.5=98.75. To inspect the last record, use:

=IF(B9>QUARTILE($B$2:$B$9,3)+1.5*(QUARTILE($B$2:$B$9,3)-QUARTILE($B$2:$B$9,1)),"Above upper fence","Not above upper fence")

For B9=100, the expected output is Above upper fence; for B8=80, the equivalent copied-row test would be Not above upper fence. This is a conventional screening rule, not proof an observation is invalid or should be removed.

Calculate the lower fence. =QUARTILE($B$2:$B$9,1)-1.5*(QUARTILE($B$2:$B$9,3)-QUARTILE($B$2:$B$9,1)) has expected result −31.25. None of the listed processing times falls below it. Some statisticians and charting tools choose different quartile definitions; document the convention when sharing these calculations.

Compare inclusive and exclusive quartiles without switching silently. Gnumeric documents QUARTILE.EXC using Hyndman–Fan method 6 (N+1), a distinct function and not an alias of QUARTILE. For the same sample, =QUARTILE.EXC(B2:B9,1) is expected to yield 12.5, while =QUARTILE(B2:B9,1) is 17.5; =QUARTILE.EXC(B2:B9,3) is expected 70, versus inclusive Q3 50. Differences are normal and can significantly change outlier flags. Gnumeric QUARTILE and QUARTILE.EXC documentation.

Dynamic windows. Using absolute references such as $B$2:$B$9 prevents moving the sampling window when you copy the formulas. It does not exclude later edits to those cells. If you need consistent month-to-month analysis, keep documented snapshots of the input range.

Locale, version and cross-software compatibility

Formulas are shown in the manual’s comma-separated argument notation with period decimal points; localized number entry and separators can vary. Use Gnumeric’s data-type help and localization help when entering 1.5, 2.8 or decimal proportions in a different locale. The official manual marks QUARTILE Excel compatible; Microsoft’s modern QUARTILE.INC documentation uses the inclusive quartile convention and selector 0–4. These statements are documentation checks—not application-to-application test results. Microsoft QUARTILE.INC. QUARTILE.EXC is mathematically different; verify names and availability when converting workbooks between applications.

PERCENTILE · MEDIAN · MIN · MAX · LARGE · SMALL

• Gnumeric Statistics manual — QUARTILE, QUARTILE.EXC and PERCENTILE — syntax, interpolation methods, error rules and compatibility; accessed 2026-10-12.
• Gnumeric official functions catalogue — catalogue presence and test labels; accessed 2026-10-12.
• Gnumeric 1.12.62 official release announcement — release context; accessed 2026-10-12.
• Microsoft Excel QUARTILE.INC documentation — inclusive-method compatibility comparison; accessed 2026-10-12.

The syntax and behaviour are based on the Gnumeric references cited above. The sample calculations were independently checked; they are expected results, not outputs observed in Gnumeric. Test locale-sensitive text conversion and imported files in your own installation. View the example-check record.

Official QUARTILE reference · Editorial standards