Free, privacy-first
Last updated:
Run descriptive statistics, percentile analysis, and outlier checks on numeric datasets.
What this tool helps you answer
Computes the full suite of descriptive statistics, central tendency, spread, shape, percentiles, and IQR-based outlier detection, from a pasted or typed numeric dataset.
Use the model, assumptions, metrics, and warnings together before acting on the output.
Mean = (Σxᵢ) / nNext step
Run descriptive statistics, percentile analysis, and outlier checks on numeric datasets.
Editorial review
This page combines the live tool, input guidance, worked examples, and operating limits so Statistics Calculator stays useful even before users interact with the calculator.
Reviewed by Klartext Tools against the current Statistics Calculator workflow on 2026-03-02.
Last updated:
Use with judgment
Page scope
The dataset 12, 15, 14, 19, 21, 18, 17 has mean 16.57, median 17, no outliers, and a mild positive skew.
Mean ≈ 16.57, median = 17, sample standard deviation ≈ 3.05, no IQR-flagged outliers.
Change the last value from 17 to 45 to introduce a strong outlier and see how the mean shifts away from the median.
Adding an extreme value demonstrates how Tukey fences flag outliers and how the median stays stable while the mean shifts.
Mean ≈ 25.1, median = 17.5, value 85 flagged as outlier by Tukey fence.
Raise the outlier factor k to 3.0 to see when only extreme outliers are flagged.
Paste your data, set the variance model, and run the analysis to get the full descriptive statistics output.
Enter numeric values in the dataset field, separated by commas, spaces, tabs, semicolons, or line breaks. You can paste directly from a spreadsheet column: select a column range and paste.
Select Sample (n−1) if your data is a random sample from a larger population. Select Population (n) only if your data represents the entire population of interest.
Adjust the percentile target (default 90th percentile), trimmed mean cutoff, histogram bin count, and outlier factor k. The defaults work well for most datasets.
The output shows central tendency, spread, shape, and outlier metrics in a structured table. Outlier-flagged values are listed separately so you can investigate them in context.
Use this seven-value dataset to verify all key metrics before analysing your own data.
The dataset 12, 15, 14, 19, 21, 18, 17 has mean 16.57, median 17, no outliers, and a mild positive skew.
Sample inputs
Sample outcome: Mean ≈ 16.57, median = 17, sample standard deviation ≈ 3.05, no IQR-flagged outliers.
Change the last value from 17 to 45 to introduce a strong outlier and see how the mean shifts away from the median.
Adding an extreme value demonstrates how Tukey fences flag outliers and how the median stays stable while the mean shifts.
Sample inputs
Sample outcome: Mean ≈ 25.1, median = 17.5, value 85 flagged as outlier by Tukey fence.
Raise the outlier factor k to 3.0 to see when only extreme outliers are flagged.
Summary statistics mean different things in different data contexts. Reporting a mean and standard deviation on a skewed distribution is actively misleading. It implies symmetry that may not exist. A median and IQR tells a completely different story from the same data. This calculator computes the full descriptive statistics set, central tendency, spread, skewness, kurtosis, and percentiles, so you can choose the representation that honestly describes your data rather than defaulting to the first two statistics that come to mind.
The statistics calculator takes a pasted or typed list of numbers, parses it (accepting commas, spaces, tabs, semicolons, or line breaks as separators), and computes the following: count, sum, mean, median, mode, geometric and harmonic mean, trimmed mean, variance, standard deviation, coefficient of variation, skewness, excess kurtosis, min, max, range, Q1, Q2, Q3, interquartile range, a user-specified percentile, Tukey-fence outlier detection, and a histogram distribution across a configurable number of bins. Results are displayed in a structured table and can be exported as JSON or CSV.
Central tendency metrics (mean, median, mode) describe the typical value in the dataset. The mean is pulled by extreme values; the median is more robust. Spread metrics (standard deviation, IQR, range) describe how far values scatter from the center. The IQR is less sensitive to outliers than the standard deviation. Shape metrics (skewness, kurtosis) describe asymmetry and tail weight. Positive skewness means a long right tail; excess kurtosis above 0 means heavier-than-normal tails.
This guide explains how to solve and interpret quadratic equations from setup to root analysis.
Use this comparison to decide whether you need exact root diagnostics or broader curve visualization.
Students do not need a giant software stack for most statistics homework. They need a smaller set of tools that help them calculate descriptive stats clearly, test probability cases, visualize relationships, and check supporting math without turning the assignment into a copy-paste mess.
Math and science calculators for equations, graphing, probability, statistics, and unit conversions.
Model discrete success scenarios with exact binomial probabilities and distribution stats.
Plot any expression in x and inspect turning points, zero crossings, and integral estimates.
Solve quadratic equations exactly with full parabola analysis and vertex details.
If the job spills into another category, these tools help with the next step.
Model long-term growth from starting capital, recurring contributions, and inflation before you commit to a savings plan.
Open toolProject how a starting balance and regular monthly contributions grow with compound interest over any time horizon.
Open toolProject your retirement savings balance from a current portfolio, monthly contributions, expected return, and inflation rate.
Open toolEstimate DevEx cash value from eligible Earned Robux, or work backward from a payout target using a clear rate assumption.
Open tool