AZ Tools

Descriptive Statistics Calculator

Everyday

Most real-world questions about a dataset come down to two things: where is the center, and how spread out is it. This calculator answers both at once. Paste numbers separated by commas, spaces, or new lines and the tool returns the count, sum, three measures of central tendency (mean, median, mode), the full five-number summary (min, Q1, median, Q3, max), the interquartile range, both sample and population variance and standard deviation, geometric and harmonic means where they're defined, the coefficient of variation, and the sample skewness. It's the calculator equivalent of a STDEV / QUARTILE pass in a spreadsheet, but without having to pick the right formula name or remember whether your version takes N or N − 1 in the denominator. Quartiles use linear interpolation (the standard exclusive method, equivalent to numpy's default and Excel's QUARTILE.INC). All computation happens locally in your browser; no values are uploaded.

Central tendency

Count (n)

10

Sum

159

Mean

15.9

Median

15.5

Mode

4, 8, 16, 23 (×2)

Spread

Min

4

Max

42

Range

38

Variance (sample)

132.3222

Variance (pop.)

119.09

Std Dev (sample)

11.5031

Std Dev (pop.)

10.9128

Coefficient of var.

72.35%

Quartiles & IQR

Q1 (25th pct.)

8

Median (Q2)

15.5

Q3 (75th pct.)

21.25

IQR (Q3 − Q1)

13.25

Other measures

Geometric mean

12.4203

Harmonic mean

9.5018

Skewness (sample)

1.29

Sample-based formulas are highlighted in green — those are the defaults for inferential work. CV (coefficient of variation) is unit-free, useful for comparing spread across datasets with different scales.

How to use

  1. Paste your data — numbers separated by commas, spaces, semicolons, or newlines all work; non-numeric tokens are ignored.
  2. Read the central-tendency block (mean, median, mode) to locate the middle of the distribution.
  3. Use the spread block (standard deviation, variance, range, coefficient of variation) to gauge how tightly the data clusters around the mean.
  4. Check the quartiles block for the five-number summary, useful for spotting outliers (anything beyond Q1 − 1.5 × IQR or Q3 + 1.5 × IQR is the classic Tukey fence).

Frequently asked questions

When should I use sample vs. population standard deviation?
Use sample standard deviation (divides by N − 1) when your numbers are a sample drawn from a larger population and you want to estimate the population's spread — that's the default in spreadsheets, statistics courses, and most scientific software. Use population standard deviation (divides by N) only when your numbers literally are the entire population (e.g., the grades of every student in a class you're describing, not inferring from).
Why is the mode shown as 'no mode' sometimes?
If every value appears exactly once, this calculator reports no mode, because there is no most-frequent value. Some textbooks call every value a mode in that case, but the 'no mode' convention is more useful in practice.
Which quartile method is this?
Linear interpolation between sorted values — the (N − 1) × q position, also called the exclusive or Tukey hinges-equivalent method. It matches numpy.quantile's default and Excel's QUARTILE.INC. Other tools (Excel's QUARTILE.EXC, the Type 6 method in R) can give slightly different numbers for small datasets.
What does the coefficient of variation tell me?
It expresses the standard deviation as a percentage of the mean, so you can compare spread across datasets that have different units or scales. A CV of 10% on monthly sales is the same relative dispersion as a CV of 10% on widget weights, even though the raw standard deviations are in different units.
Why are geometric and harmonic means sometimes blank?
Both are only defined when all values are positive — the geometric mean requires multiplying values, and the harmonic mean requires their reciprocals. If your data contains zeros or negatives, those cells stay blank rather than show a misleading number.

Related tools