Descriptive Statistics Calculator
Calculate and interpret mean, median, variance and standard deviation while observing how data changes, analytical assumptions and an extreme value affect the statistical story.
Learn the measures by changing the data.
Describe centre and spread without losing sight of the data.
You will inspect a small business dataset, manipulate observations, reveal central-tendency and dispersion calculations, compare population and sample formulas, and test how an extreme value changes the conclusions.
Descriptive statistics summarize observed values; they do not establish causation or guarantee that the sample represents a wider process.
Descriptive Statistics — Step by Step
Eight locked stages move from data inspection to centre, dispersion, formula choice, an outlier challenge and management interpretation.
Distribution, Centre and Spread
Reveal the business context to begin.
Observation-level calculation table
Input values are visible from the scenario. Deviation and squared-deviation fields remain hidden until the variance stage has been revealed.
| Observation | Value | Deviation from mean | Squared deviation |
|---|
Build your own eight-value dataset
Experiment Mode is fully isolated from the guided demonstration. Change any observation and switch between population and sample formulas; all experiment results update immediately.
Test interpretation—not just formula recall.
Descriptive statistics decision cues
Mean
Σx ÷ n. Uses every value and is sensitive to extreme observations.
Median
Middle ordered value; average the two middle values when n is even. More resistant to outliers.
Population Variance
σ² = Σ(x−μ)² ÷ n when the observed values are the complete population being described.
Sample Variance
s² = Σ(x−x̄)² ÷ (n−1) when the observed values are a sample used to estimate wider variation.
Standard Deviation
Square root of variance. Expresses dispersion in the original measurement unit.
Outlier Cue
If mean and median separate sharply and spread increases, inspect extreme values before summarising performance.
Mean, median, variance and standard deviation are most useful when the analyst also checks distribution shape, outliers and whether the formula matches a population or a sample.