Descriptive Statistics Calculator

Paste a column of numbers and get every summary statistic you are likely to need: centre, spread, shape, quartiles and outliers. You also get a histogram with a normal curve and a box plot. Data can be separated by commas, spaces, tabs, semicolons or new lines, and a header row copied from Excel is ignored automatically.

How to use the descriptive statistics calculator

  1. Type or paste your data into the box, or upload a CSV file. The counter under the box confirms how many values were read.
  2. Choose a quartile method. Textbooks and the TI-84 take the median of each half; Excel’s QUARTILE.INC and R use linear interpolation; SPSS and QUARTILE.EXC use the exclusive method. They can give slightly different Q1 and Q3 values for the same data.
  3. Press Calculate. The headline shows the mean, median, standard deviation and sample size, followed by the full summary table and the charts.

What each statistic tells you

GroupStatisticsUse it to…
CentreMean, median, modeDescribe a typical value. Prefer the median when the data are skewed or contain outliers.
SpreadStandard deviation, variance, range, IQRDescribe how much values vary. The IQR is resistant to outliers; the SD is not.
PrecisionStandard error, 95% confidence intervalShow how precisely the sample mean estimates the population mean.
ShapeSkewness, kurtosisCheck symmetry and tail weight before choosing a test.
Unusual valuesLower and upper fencesFlag values more than 1.5 × IQR beyond the quartiles.

Formulas

Mean: x̄ = Σx ÷ n · Sample variance: s² = Σ(x − x̄)² ÷ (n − 1) · Standard error: SE = s ÷ √n

Skewness is reported as the adjusted Fisher–Pearson coefficient G₁ and kurtosis as bias-corrected excess kurtosis G₂, which are the values Excel’s SKEW and KURT and SPSS report. A normal distribution has G₁ = 0 and G₂ = 0. As a rule of thumb, a skewness or kurtosis more than about twice its standard error suggests the data depart from normality.

Worked example

For the example data (12, 15, 11, 18, 21, 13, 16, 14, 19, 22, 35) the mean is 17.82 but the median is only 16, because the value 35 pulls the mean upwards. Taking the median of each half, Q1 = 13 and Q3 = 21, so the upper fence is 21 + 1.5 × 8 = 33, so 35 is flagged as a possible outlier. That gap between mean and median, together with a positive skewness, tells you the median is the better summary of a typical value here.

Frequently asked questions

Should I use the sample or population standard deviation?

Use the sample standard deviation (dividing by n − 1) whenever your data are a sample from a larger group, which is almost always the case in research. Use the population version only when you have measured every member of the group you care about.

Why are my quartiles different from my textbook or Excel?

There are several accepted ways to calculate quartiles. Choose the method that matches your course or software from the drop-down and the values will agree.

How do I paste data from Excel or Google Sheets?

Copy the column (including its header if you like) and paste it straight into the box. Tabs, new lines and a text header are handled automatically. If your numbers use a decimal comma, such as 1,5, they are recognised too.