Foundations of Data Science slides 📂 Introduction · 10 of 10 33 min read

Kurtosis Explained: Leptokurtic, Platykurtic & Mesokurtic

The shape statistic that measures tail heaviness — how likely extreme values are, not how "pointy" a curve is. This tutorial covers the fourth-moment formula, excess kurtosis (K−3), the three types (leptokurtic >3, mesokurtic =3, platykurtic <3), why fat tails mean real-world risk, a worked example where one outlier dominates, kurtosis vs skewness, and code — with animated diagrams.

📉

Kurtosis Explained

The shape statistic that measures tail heaviness — how likely extreme values are. It's the reason "once-in-a-century" market crashes keep happening every few years.
Leptokurtic Mesokurtic Platykurtic Fat Tails

Press Next → or use ← → arrow keys

Section 01

The Intuition — Why Tails Matter

The wind speeds a normal model missed
A bridge engineer models decades of wind-speed data. The mean and standard deviation look perfectly ordinary — but buried in the record are a handful of freak gusts far beyond what a normal bell curve would ever predict. Those rare, violent extremes — the heavy tails — are exactly what a bridge must survive.

Kurtosis is the statistic that measures them. It captures how much of a distribution's action lives out in the tails — the propensity for rare, extreme events that mean and spread completely overlook.
💥
Fat Tails, Real Money

The 2008 crisis featured market moves that "normal" risk models rated as once-in-the-history-of-the-universe rare — yet they happened. The models ignored kurtosis. Financial returns have fat tails, so extreme days occur far more often than a bell curve predicts.

Section 02 · The Three Shapes

Lepto, Meso & Platykurtic

Leptokurtic (K > 3) Mesokurtic (K = 3) Platykurtic (K < 3) same mean & spread — different tails
📐
It's About The Tails, Not The Peak

The common myth is that kurtosis measures how "pointy" a distribution is. It doesn't — it measures tail weight. Leptokurtic has heavy tails (more outliers), platykurtic has light tails (fewer), and mesokurtic is the normal-distribution baseline. The tall peak of a leptokurtic curve is a side-effect of mass being pulled from the shoulders into the tails.

Section 03 · Formula

The Fourth Standardized Moment

Kurtosis
K = [ Σ(xᵢ − μ)⁴ / N ] / σ⁴
The average fourth power of deviations, standardized by σ⁴.
Excess kurtosis (Fisher)
K_excess = K − 3
Subtract 3 so the normal distribution sits at 0 — the reference point.
4️⃣
Why The Fourth Power?

Raising each deviation to the fourth power massively amplifies points far from the mean: a value twice as far contributes sixteen times as much. That's what makes kurtosis a tail-heaviness detector — and also why a single outlier can dominate it. For a normal distribution the maths works out to exactly K = 3, the baseline everything is compared against.

Section 03 · Reference

The Three Types, Side By Side

TypeKurtosisExcessTailsExamples
Leptokurtic> 3> 0Heavy / fatStock returns, insurance claims, earthquakes
Mesokurtic= 3= 0ModerateHeights, IQ, measurement error (normal)
Platykurtic< 3< 0Light / thinUniform data, capped scores, tight tolerances
🔤
The Greek Roots Help

Lepto = thin (a thin, tall waist with energy escaping into the tails); platy = broad/flat (think "plateau"); meso = middle. Match the word to the silhouette and you'll never mix them up.

Section 04 · Why It Matters

Fat Tails = Extreme Events Are Common

"extreme" region (far tail) Leptokurtic — tail stays fat Normal — tail vanishes fast more area out here = more outliers
⚠️
The Same Middle, A Very Different Tail

Two distributions can share the same mean and standard deviation, yet the leptokurtic one keeps real probability mass far out in the tail where the normal curve has essentially hit zero. That extra tail area is what turns "impossible" events into merely "rare" ones — the mathematical signature of financial crashes, insurance mega-claims, and structural failures.

Section 05 · Worked Example

One Outlier Dominates The Kurtosis

(xᵢ − μ)⁴ contribution per reading · μ = 22°C 10,000 256 32°C 18–23°C readings ≈ 0–256 each
🌡️
Temperatures [18…23, 32] → Excess K = 3.28

Nine mild readings plus one 32°C spike. That single outlier's fourth-power contribution is 10,000 out of a total 10,292 — it alone drives raw kurtosis to 6.28 (excess 3.28, firmly leptokurtic). One point, and the whole dataset "looks" heavy-tailed. Kurtosis is exquisitely sensitive to outliers — always visualize before trusting it.

Section 05 · The Scale

Reading Excess Kurtosis On A Number Line

0 · normal (mesokurtic) ← platykurtic (thin tails) leptokurtic (fat tails) → −1.2uniform ≈ 0normal +3.3temp example +5.8t(3) returns
🎯
Zero Is Your Anchor

On the excess scale, 0 is the normal distribution. Negative means lighter tails than normal (platykurtic — like a uniform distribution at −1.2); positive means heavier (leptokurtic — like a Student-t at +5.8). The further from zero, the more the tails depart from the bell.

Section 06 · Shape Duo

Kurtosis vs Skewness

PropertyKurtosisSkewness
MeasuresTail heaviness (outlier propensity)Asymmetry (which way it leans)
Moment4th central moment3rd central moment
Normal value3 (raw) / 0 (excess)0
Outlier sensitivityExtreme (4th power)High (3rd power)
Answers"How extreme?""Which direction?"
🧭
Two Numbers Finish The Shape

Mean and standard deviation describe where data sits and how spread it is. Skewness then tells you which way it leans, and kurtosis how heavy its tails are. Together the four give you a complete shape diagnostic — never rely on mean and variance alone.

Section 07 · Applications

Where Fat Tails Bite

💹
Financial Risk
Returns are leptokurtic. Assuming normality underestimates crash probability — the core mistake behind 2008.
🛡️
Insurance & Engineering
Claim sizes and structural loads have heavy tails; kurtosis flags whether rare catastrophic events lurk.
🤖
ML & Fraud
High kurtosis in a feature warns of outlier-heavy data — vital before assuming normality or spotting fraud spikes.
📉
"25-Sigma" Events Aren't Really 25-Sigma

When a risk model calls a market move a "25-standard-deviation event," it's not that the impossible happened — it's that the model used a thin-tailed normal distribution on fat-tailed data. Measuring kurtosis first tells you when a normal assumption will dangerously understate real-world risk.

Section 08 · Pitfalls

Three Traps To Avoid

❌ The Trap✅ The Reality
"Kurtosis measures how pointy the peak is"It measures tail weight — the peak is a side-effect
Assuming your tool returns raw kurtosisSciPy/Pandas/Excel default to EXCESS (normal = 0)
Trusting a high value on messy dataOne outlier can fake leptokurtosis — always plot
🔢
Raw Or Excess? Always Check

A kurtosis of "0" and a kurtosis of "3" can mean the same normal distribution — the first is excess, the second is raw. Before interpreting any kurtosis number, confirm which convention your tool uses (in SciPy, that's the fisher parameter), or you'll be off by exactly 3.

Section 09 · Code

Kurtosis In Python

from scipy import stats
import numpy as np

data = [18, 20, 20, 21, 21, 21, 22, 22, 23, 32]

stats.kurtosis(data)                 # 3.28  → EXCESS (fisher=True, default)
stats.kurtosis(data, fisher=False)   # 6.28  → RAW (normal = 3)

# ── compare three shapes ──
np.random.seed(42)
stats.kurtosis(np.random.normal(size=10000))        # ≈  0.02  mesokurtic
stats.kurtosis(np.random.standard_t(3, 10000))     # ≈  5.85  leptokurtic
stats.kurtosis(np.random.uniform(-3, 3, 10000))   # ≈ −1.19  platykurtic
🐼
Pandas Too — But Sample-Corrected

Series.kurt() and df.kurt() also return excess kurtosis, but with a sample-size correction, so the number can differ slightly from SciPy's on small datasets. As always, check the docs for which formula a tool uses before comparing values across libraries.

Section 10 · Golden Rules

Six Rules For Kurtosis

🏅 Kurtosis, Distilled
1It's tail weight, not peakedness. High kurtosis = more extreme outliers, full stop.
2Know raw vs excess. Normal = 3 (raw) or 0 (excess); most tools default to excess.
3Excess > 0 heavier, < 0 lighter tails than a normal distribution — that's your baseline.
4One outlier can dominate it (4th power) — always visualize before trusting a value.
5Fat tails mean real risk. Never assume normality on leptokurtic finance/insurance data.
6Pair with skewness for a full shape picture beyond mean and variance.
Wrap-Up

You Now Understand Kurtosis

tailsNot peakedness
4thStandardized moment
K−3Excess kurtosis
>0Lepto · fat tails
<0Platy · thin tails
plot!Outlier-sensitive
🎯
The Through-Line

Kurtosis is the fourth-moment shape statistic that measures tail heaviness — how prone a distribution is to extreme values. Leptokurtic (>3) means fat tails and real risk; platykurtic (<3) means thin tails; mesokurtic (=3) is the normal baseline. It's outlier-sensitive by design, so read it alongside a plot and its partner, skewness.

📚
Where To Go Next

Pair kurtosis with skewness for full shape diagnostics, connect both to the normal distribution and the empirical rule, and explore fat-tailed distributions (Student-t, power laws) that model real financial and extreme-event data.

📉 End of tutorial · Press to review, or click Restart

You have completed Introduction. View all sections →