AnyTool
Your files never leave your device. All processing happens locally in your browser.

How do I calculate descriptive statistics online?

Paste or type your numbers — separated by commas, spaces, tabs or new lines — into AnyTool Statistics Calculator and it returns a full descriptive-statistics summary instantly. You get central tendency (mean, median, mode, midrange, geometric and harmonic means), dispersion (both population and sample variance and standard deviation, mean absolute deviation, coefficient of variation and standard error), position (Q1/Q2/Q3, IQR, a custom percentile you choose, and 1.5·IQR outlier fences) and shape (skewness and excess kurtosis). It also draws a histogram and a box-and-whisker plot and lists the sorted data with a frequency table. Everything is computed in your browser by a pure, unit-tested engine, so nothing is uploaded.

  • Over 30 statistics from one list of numbers, recomputed live
  • Population (÷N) and sample (÷n−1) variance and standard deviation, clearly distinguished
  • Quartiles, IQR, a custom percentile and 1.5·IQR outlier detection
  • Pure-SVG histogram and box-and-whisker plot, plus a frequency table
  • 100% in your browser — no upload, no signup, works offline

What is

Statistics calculator

A statistics calculator summarises a list of numbers with descriptive statistics: measures of central tendency such as the mean, median and mode; measures of dispersion such as the variance, standard deviation, range and interquartile range; measures of position such as quartiles and percentiles; and measures of shape such as skewness and kurtosis. AnyTool implements one entirely in the browser, computing both population and sample versions, drawing a histogram and box plot, and stating when each version should be used.

Calculators

Related terms

MeanMedianStandard deviationQuartileSkewness

Frequently Asked Questions

Population standard deviation divides by N and is used when your data is the whole group; sample standard deviation divides by n − 1 and is used when your data is a sample of a larger group.

Both measure how spread out numbers are around the mean, but they divide the summed squared deviations by a different amount. The population standard deviation (σ) divides by N, the full count, and is correct only when your data covers every member of the group you care about. The sample standard deviation (s) divides by n − 1 — the Bessel correction — because a sample tends to under-estimate the true variability of the larger population it came from; dividing by n − 1 instead of n compensates for that bias. AnyTool Statistics Calculator shows both side by side, and bases the coefficient of variation and standard error on the sample standard deviation, so you can pick the right one for your situation.

It sorts the data, takes the middle value as the median, and uses linear interpolation between sorted points for quartiles and any percentile you enter.

AnyTool first sorts your numbers ascending. The median is the middle value, or the average of the two middle values when the count is even. Quartiles and percentiles use the linear-interpolation method (the same one Excel’s PERCENTILE.INC and NumPy’s default use): a percentile p maps to the position (n − 1)·p, and the value is interpolated between the two sorted points around that position. Q1, Q2 and Q3 are the 25th, 50th and 75th percentiles, the interquartile range is Q3 − Q1, and any value below Q1 − 1.5·IQR or above Q3 + 1.5·IQR is flagged as an outlier on the box plot.

If every number appears once there is no mode; if two or more values tie for the highest frequency the data is multimodal and all of them are reported.

The mode is the most frequently occurring value. When all of your numbers are distinct, no value repeats, so AnyTool honestly reports “no mode” rather than picking one arbitrarily. When two or more values share the highest count, the data is bimodal or multimodal and the calculator lists every modal value along with how many times it occurs. Unlike the mean and median, the mode can be undefined or non-unique, which is why it always needs context to interpret.

Yes — every calculation runs in your browser with no server call, and the page works offline after first load.

AnyTool Statistics Calculator parses your numbers and computes every statistic locally in JavaScript on a pure, unit-tested engine, so the data you paste is never sent to a server, there is no account or tracking, and the tool keeps working without a connection once it has loaded. Results use IEEE-754 double precision and are rounded only for display.

Detailed Explanation

Methodology

How the Statistics Calculator Computes Each Measure

AnyTool Statistics Calculator runs a pure, unit-tested engine entirely in the browser. It parses the input on commas, spaces, tabs, semicolons and new lines, keeping only finite numbers, then computes a full descriptive summary. The mean is the sum over the count; the median is the middle of the sorted data (or the average of the two middle values); the mode lists the most frequent value(s). Variance is the average squared deviation from the mean — divided by N for the population version and by n − 1 (Bessel’s correction) for the sample version — and the standard deviation is its square root. Quartiles and any custom percentile use linear interpolation on the sorted array (the Excel PERCENTILE.INC / NumPy default method), the interquartile range is Q3 − Q1, and skewness and excess kurtosis use the bias-corrected sample moment formulas. Everything is computed at full double precision and rounded only for display.

  • Population variance ÷ N, sample variance ÷ (n − 1)
  • Median and quartiles from the sorted data with linear interpolation
  • Custom percentile via the Excel/NumPy inclusive method
  • Bias-corrected sample skewness and excess kurtosis
  • Pure, unit-testable engine — no DOM, no server
How It Works

Every Statistic, Grouped by Purpose

The summary is organised into four groups. Central tendency: mean, median, mode (single, multimodal or none), midrange, geometric mean, harmonic mean and root mean square. Dispersion: population and sample variance and standard deviation, mean absolute deviation, coefficient of variation (based on the sample standard deviation), standard error of the mean, range and sum of squares. Position: minimum, Q1, Q2 (median), Q3, maximum, interquartile range, a percentile you type in, and the 1.5·IQR lower and upper fences with any outliers. Shape: skewness (direction and degree of asymmetry) and excess kurtosis (tailedness relative to a normal distribution). A pure-SVG histogram and box-and-whisker plot visualise the distribution, and a collapsible panel lists the sorted values and a frequency table.

  • Central tendency, dispersion, position and shape in one view
  • Geometric and harmonic means computed only for positive data
  • Custom percentile plus 1.5·IQR outlier detection
  • SVG histogram and box-and-whisker plot
  • Sorted data and frequency table on demand
Limitations

Sample vs Population, and Honest Limits

The most common mistake in descriptive statistics is mixing up sample and population formulas, so AnyTool shows both and explains the choice. Use the sample statistics (÷ n − 1) when your numbers are a sample of a larger group you want to generalise about; use the population statistics (÷ N) only when the data is the entire population. The coefficient of variation and standard error shown here are based on the sample standard deviation. The mode is reported as “no mode” when every value is unique and may be multimodal; skewness needs at least three values and excess kurtosis at least four, and both always need context to interpret. The tool computes descriptive statistics only — it does not run inferential tests such as t-tests, ANOVA, regression or confidence intervals — and uses IEEE-754 double precision, so results are rounded for display.

  • Sample (÷ n − 1) for samples, population (÷ N) for whole populations
  • CV and standard error use the sample standard deviation
  • “No mode” when all values are unique; multimodal data lists every mode
  • Skewness needs n ≥ 3, excess kurtosis needs n ≥ 4
  • Descriptive only — no t-tests, ANOVA or regression
Privacy & Security

Privacy and Offline Use

Because the parser and every statistical routine run in the browser, nothing you paste is sent to a server, there is no account or tracking, and the page keeps working offline after first load. The numbers and results live only in the page and disappear on reset or reload. The engine is shared and unit-testable, so its behaviour is consistent and verifiable.

Descriptive statistics: in-browser (AnyTool) vs typical online calculators
CapabilityAnyToolTypical online calculators
Where it runs100% in your browserOften server-side
Sample vs populationBoth shown and explainedSometimes only one
Quartile methodLinear interpolation (Excel/NumPy)Varies, rarely stated
VisualsSVG histogram and box plotOften none or image-only
Outlier detection1.5·IQR fences flaggedFrequently omitted
Custom percentileYes, any 0–100Often fixed quartiles only
Works offlineYes (PWA)No
Cost / signupFree, no signupOften ad-heavy or gated

AnyTool computes every statistic locally with a stable, unit-tested engine and uploads nothing.