KURT function

KURT returns the kurtosis (excess tailedness) of a dataset, measuring whether values cluster at extremes or center.

=KURT(number1, ...)

Generate a KURT formula

Describe what you need. The generator will reach for KURT where KURT is the right tool, and tell you when it is not.

How to get a better answer
  • Name your columns by letter and by header: "column F (Net Value)" beats "the amount column".
  • State every condition, including the negatives — "not cancelled" changes the formula's shape.
  • Say where the data starts if it is not row 1, and whether it will grow.
  • Check the settings above match your spreadsheet: the wrong argument separator is a syntax error on your machine.

Arguments

How KURT reads its arguments
number1requiredKURT →
ArgumentRequiredDescription
number1RequiredRequired. A numeric value or cell reference; text and blanks are ignored by KURT.
...RepeatingOptional. Additional numeric values or ranges; up to 255 arguments allowed. At least 4 numeric data points required; fewer returns #DIV/0!.

Returns

A number representing the excess kurtosis of the dataset; positive indicates heavier tails than normal, negative indicates lighter tails.

Availability

Excel: All · Google Sheets: Supported

Worked examples

1. Analyze maintenance cost distribution

VehicleCost
Car A150
Car A180
Car A165
Car B145
Car B220
Car B155
Car C175
Car C195
Car C160
=KURT(150, 180, 165, 145, 220, 155, 175, 195, 160)

Result: 0.86

The nine maintenance costs range from 145 to 220. Kurtosis of 0.86 (positive) indicates slightly heavier tails, meaning prices occasionally spike to extremes beyond a normal distribution, signaling unpredictable budget swings.

2. Evaluate spread in service intervals

Interval (miles)
15000
15000
16000
14000
15000
15000
=KURT(15000, 15000, 16000, 14000, 15000, 15000)

Result: -0.31

Service intervals cluster tightly around 15,000 miles (range 14k–16k). Negative kurtosis (–0.31) indicates a platykurtic distribution—narrow spread with no extreme outliers, suggesting highly predictable maintenance scheduling.

3. Assess odometer variation at service time

Odometer at Service
15000
30000
45000
12000
28000
42000
18000
33000
48000
=KURT(15000, 30000, 45000, 12000, 28000, 42000, 18000, 33000, 48000)

Result: -0.42

The nine odometer readings are fairly evenly spaced from 12,000 to 48,000 miles. Negative kurtosis (–0.42) confirms a platykurtic distribution—fleet vehicles accumulate mileage uniformly without clustering at extremes.

Common errors

Which KURT error are you seeing?
KURT returned an error#DIV/0!
Expand your data range or argument list to include at least 4 numeric values. Empty cells and text are ignored but don't count; ensure you have 4+ numbers.
#VALUE!
Convert text to numbers or remove non-numeric columns. If using date columns, ensure they're stored as numbers, not text. Use numeric data only.
#NUM!
Ensure your data contains variation. If all costs are 160, 160, 160, 160, replace some values with different numbers. Use a dataset with measurable range.
ErrorWhy it happensHow to fix it
#DIV/0!KURT requires at least 4 numeric data points. Supplying fewer (e.g., 1, 2, or 3 values) causes a division error because kurtosis cannot be calculated from insufficient samples.Expand your data range or argument list to include at least 4 numeric values. Empty cells and text are ignored but don't count; ensure you have 4+ numbers.
#VALUE!One or more arguments contain non-numeric data (text, dates formatted as text, or other non-numeric types). KURT cannot compute kurtosis with non-numeric input.Convert text to numbers or remove non-numeric columns. If using date columns, ensure they're stored as numbers, not text. Use numeric data only.
#NUM!All data points are identical, producing zero variance. Kurtosis is undefined when there is no spread or dispersion in the dataset.Ensure your data contains variation. If all costs are 160, 160, 160, 160, replace some values with different numbers. Use a dataset with measurable range.

Tips and when to use something else

  • KURT calculates excess kurtosis: 0 = normal distribution, positive = heavier tails (outliers more likely), negative = lighter tails (clustered values). Use it to assess tail risk in financial or operational data.
  • Empty cells and text are silently ignored; only numeric values count toward the 4-minimum threshold. If you have 2 numbers and 2 blanks, you'll get #DIV/0!.
  • For small samples (n < 30), kurtosis is highly sensitive to outliers. If extreme values skew your result, verify they're valid before trusting kurtosis analysis.
  • KURT measures tailedness; use SKEW instead if you want to measure asymmetry (left vs. right imbalance). For simple central tendency, use AVERAGE or MEDIAN.

Related functions

AVERAGEAVERAGE calculates the arithmetic mean of numbers, ignoring text and logical values; returns a single numeric value representing the average.MEDIANMEDIAN returns the middle value in a sorted list of numbers, or the average of the two middle values if the count is even.MODE.SNGLReturns the most commonly appearing numeric value in a dataset, ideal for identifying the most frequent priority level, rating, or resolution time.LARGELARGE returns the k-th largest value in an array, where k=1 is the maximum, k=2 is the second-largest, and so on.SMALLSMALL returns the k-th smallest value from an array, where k=1 gives the minimum and higher k values give progressively larger results.

Frequently asked questions

What does a kurtosis value of 0 mean?
Kurtosis of 0 (excess kurtosis) indicates a normal, bell-shaped distribution with average tailedness. Positive values show heavier tails (leptokurtic); negative show lighter tails (platykurtic).
How many data points does KURT need?
KURT requires at least 4 numeric values. Fewer than 4 returns #DIV/0!. Empty cells and text are ignored but don't count toward the 4-point minimum.
Should I use KURT or SKEW to analyze my data?
Use SKEW to measure asymmetry (is the left tail longer than the right?). Use KURT to measure tailedness (are values concentrated at extremes or center?). Both describe distribution shape but answer different questions.
Why does KURT return a different value when I change one data point?
Kurtosis is highly sensitive to outliers and sample composition. Removing an extreme value or adding a new one can significantly shift kurtosis because it measures tail behavior directly.

Need a different formula?

The full generator is not scoped to one function — describe any spreadsheet problem and it will pick.

Open the formula generator

Reviewed 2026-09-17