Measures of location & spread 2.0
About this app
Rebuild 2.0 (preview): location and spread, target parameters n, x̄, s, skewness and kurtosis via sliders.
The statistics
The mean is the balance point of the data: only at x̄ do deviations to the left and right cancel, Σ(xᵢ − x̄) = 0. The standard deviation s measures spread but says nothing about shape. Shape is described by skewness g₁ = m₃/m₂^1.5 and excess kurtosis g₂ = m₄/m₂² − 3, built from the central moments mₖ. Positive skewness means a long right tail; positive excess kurtosis means heavier tails than a normal distribution. Every distribution satisfies g₂ ≥ g₁² − 2.
What you see
The data points sit on a seesaw whose pivot is the mean. Above it you can show a histogram or the squared deviations, along with the deviations xᵢ − x̄ and a bracket x̄ ± s. On a shape map you drag a ring: horizontally it changes skewness, vertically kurtosis, and the impossible region g₂ < g₁² − 2 is blocked. The app then generates a sample with exactly the same x̄ and s. Statistics include the median, mean absolute deviation, IQR, quartiles and a comparison with Excel’s SKEW and KURT.
Things to try
Drag the ring on the shape map from normal to right-skewed and watch the points rearrange while mean and standard deviation stay fixed. Try flat and peaked to see the difference in kurtosis. Then drag a single point outwards: the seesaw tips until the pivot catches up. Add an outlier and compare the statistics with and without it. Clicking the seesaw places a point, and a double click removes one.
Frequently asked questions
- What is the skewness of a distribution?
- Skewness measures how asymmetric a distribution is. With positive (right) skew the right tail is longer and the mean usually lies to the right of the median. Negative skew is the reverse; a symmetric distribution has a skewness of 0.
- What does kurtosis describe?
- Kurtosis describes how much weight lies in the tails of a distribution. Excess kurtosis is scaled so that the normal distribution has a value of 0. Positive values mean heavier tails and more extreme values, negative values a flatter distribution with light tails.
- Why is the mean the balance point of the data?
- The deviations of all values from the mean always sum to zero. If the values were equal weights on a seesaw, the mean is exactly the point where it balances. A distant value has a long lever arm and shifts the balance point strongly.
- What is new in version 2.0 of the app?
- Version 2.0 is a rebuild (preview): the data sit on a seesaw with the mean as its pivot, and a shape map controls skewness and kurtosis while x̄ and s stay exactly fixed. It adds squared deviations, a bracket x̄ ± s and a comparison with Excel’s SKEW and KURT functions.
Subject: Statistics
More from Statistics
- Anscombe's quartet
- Bias-variance / overfitting
- Box plot workshop
- Geometric mean
- Law of large numbers
- Histogram workshop
- Hypothesis test & p-value
- Confidence interval
A VisuApp by heyprof: interactive, free in your browser, no sign-up. What is a VisuApp? · All apps