Descriptive Statistics Calculator: Mean, Median, SD, Quartiles and More
Paste a column from Excel and instantly get every summary statistic you need for a thesis table, plus a histogram and a box plot you can download.
How to use the descriptive statistics calculator
- Paste your numbers into the box, or use Paste from Excel or Upload CSV / Excel to pick a column from your spreadsheet. Example data is loaded so you can see how it works.
- Optionally type the variable name, which is used in the summary sentence and chart labels.
- Click Calculate to see the full summary table, a histogram and a box plot.
- Copy the table into Excel, copy the sentence into your results, or download the charts as PNG or SVG.
What each statistic tells you
| Statistic | What it means | When to report it |
|---|---|---|
| Mean and SD | The average and how spread out values are around it | Roughly symmetric data without strong outliers |
| Median and IQR | The middle value and the range of the middle 50% | Skewed data, or data with outliers |
| Standard error (SE) | How precisely the sample mean estimates the population mean | Error bars and confidence intervals, not for describing spread |
| Skewness | Asymmetry: positive means a long right tail | Checking normality before a t-test or ANOVA |
| Kurtosis (excess) | Heavy (> 0) or light (< 0) tails compared with a normal curve | Checking normality |
Formulas used
Frequently asked questions
What is the difference between sample and population standard deviation?
The sample SD divides by n − 1 and is what you almost always want when your data are a sample from a larger population. The population SD divides by n and is only correct when you have measured every member of the population.
Why do my quartiles differ from SPSS?
There are several ways to calculate quartiles. This tool uses linear interpolation (R’s default and Excel’s QUARTILE.INC). SPSS uses a weighted average method, so small differences are normal, especially with small samples.
How do I know if my data are normally distributed?
Look at the histogram and the skewness and kurtosis values. Values of skewness between about −1 and +1 are usually acceptable for t-tests and ANOVA. For a formal test, use Shapiro–Wilk in R, SPSS or JASP.
What should I do with outliers?
First check whether they are data entry errors. If they are real, keep them and consider reporting the median and IQR, or run the analysis with and without them (a sensitivity analysis). Never delete outliers just because they make results look worse.
Can I paste data from Excel or upload a file?
Yes. Copy a column in Excel and paste it into the box, or click Paste from Excel or Upload CSV / Excel to load a whole sheet and choose the column. Files are read in your browser and are never uploaded or stored.
Is my data private?
Yes. Calculations happen in your browser, and nothing is uploaded.
