# Descriptive statistics calculator > How are your numbers distributed? Paste numbers and see their quartiles, spread and outliers, with a live histogram and box plot on one axis. Paste a list of numbers for the median, quartiles, IQR, standard deviation and outliers, drawn as a histogram and a box plot that share one axis. - Page: https://how.box/statistics/ - Runs entirely in the browser. - License: HowToolbox's own text and data (titles, explanations, FAQs, tool descriptions and schemas, this file) are CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/); AI training and answers are welcome. Attribute "HowToolbox (how.box)" with a link to the page used. Third-party data keeps its own terms; the name and logo are not licensed. Publisher: HowToolbox, contact@how.box. Terms: https://how.box/about/terms/ ## Inputs Answer link: https://how.box/statistics/?v={v}&w={w} - `v` (text): The numbers, separated by spaces, line breaks or semicolons. Example: `22 25 27 31 52`. - `w` (number 0 to 1e12): Histogram bin width, above 0. Example: `5`. Example answer: https://how.box/statistics/?v=22+25+27+31+52&w=5 A complete link carries the primary answer in the page HTML; a missing or invalid value shows the default page. ## Agent tools - `statistics_calculate`: Descriptive statistics of a list of numbers: count, sum, mean, median, modes, min, max, range, quartiles q1 and q3 (Hyndman–Fan type 7, the spreadsheet QUARTILE.INC rule), iqr, sample (n − 1) and population SD and variance, Tukey fences (q1 − 1.5 iqr, q3 + 1.5 iqr), the outliers outside them and the box-plot whiskers (the most extreme values inside the fences). - MCP, one POST to https://how.box/mcp: `{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"statistics_calculate","arguments":{"values":"22 25 27 31 52","bin_width":5}}}` - GET: https://how.box/mcp/run/statistics_calculate?values=22+25+27+31+52&bin_width=5 ## How it works Descriptive statistics sum up a list of numbers in a few figures. Sort the list: the median is the middle value, the first quartile Q1 has a quarter of the values below it and the third quartile Q3 three quarters. The middle half of the data lies between them, and its width, the interquartile range IQR = Q3 − Q1, measures spread without being pulled by extreme values. The mean x̄ = Σx ÷ n and the standard deviation (with n − 1 for a sample) describe the same list in the way most formulas use. A box plot draws the box from Q1 to Q3 with a line at the median. Tukey's rule marks a value as an outlier when it lies more than 1.5 × IQR below Q1 or above Q3; the whiskers reach the most extreme values inside those fences. In the example list Q1 = 30.5 and Q3 = 38.5, so IQR = 8 and the fences are 30.5 − 12 = 18.5 and 38.5 + 12 = 50.5: the 52 is an outlier. A histogram counts how many values fall in each equal-width bin, so it shows the shape: one peak or two, symmetric or skewed. Quartiles use the same interpolation as spreadsheets' QUARTILE.INC (Hyndman and Fan type 7); other textbooks split the list slightly differently, so small lists can give a slightly different Q1 or Q3. An outlier by this rule is a value worth checking, not a mistake to delete. The histogram's shape depends on the bin width, which is why it is adjustable. Definitions follow the NIST/SEMATECH e-Handbook of Statistical Methods. ## FAQ **What is the difference between the mean and the median?** The mean adds everything up and divides by the count, so one very large value pulls it up. The median is simply the middle value, so it stays put. When the mean is well above the median, the data is skewed to the right. **What happens to labels or other nonnumeric entries in my pasted data?** They are listed as invalid and left out of the calculation. Check that list before using the result, especially if you pasted a spreadsheet column with headings. **Why is there no sample standard deviation for one number?** The sample formula divides by n − 1, which is zero for one observation. The population standard deviation is still zero because that one value has no spread. **How wide should the histogram bars be?** The automatic width gives about log₂ n + 1 bars (Sturges' rule) at a round width. Narrower bars show more detail but more noise; wider bars smooth it out. Try both: a real pattern survives the change. **Should I use the sample or the population standard deviation?** Use the sample figure (dividing by n − 1) when your numbers are a sample of a larger group, which is the usual case; the population figure (dividing by n) only when the list is the whole group. Both are in the summary. More: [HowToolbox index](https://how.box/llms.txt) · [Agent Skill](https://how.box/skill.md) · [agent terms](https://how.box/about/agents/)