Skewness Indicator: Formula, Settings and How to Read It
Skewness measures the asymmetry of the distribution of the last N bar returns. A negative value means the downside tail is the heavier one — many modest advances interrupted by a few large declines — while a positive value describes the opposite shape.
Senzoukria · Indicators · Updated September 2026
Skewness ships with the Senzoukria desktop app, in the Volatility group of the indicator catalogue. It is drawn in its own panel below the chart.
What Skewness measures
The calculation is the standardised third moment, g1 = m3 divided by sigma cubed, using population moments with a divisor of N, the same convention the rest of this catalogue uses for standard deviation. No sample adjustment (adjusted Fisher-Pearson) is applied, which keeps the catalogue internally consistent; at the default window the difference is negligible. That default is 50 returns, so 51 bars are needed before anything appears, and it is set there because the shape of a distribution needs a reasonable number of observations to mean anything. If the returns in the window have exactly zero dispersion, the result is undefined and nothing is plotted, rather than a misleading 0.
The formula, as implemented
This is not a description of how the indicator is usually defined elsewhere — it is what the shipped code computes, documented next to the implementation:
Asymétrie (skewness) des N derniers rendements — moment d'ordre 3 standardisé, convention POPULATION (÷N, comme le σ du catalogue) : g1 = m3 / σ³ avec m_p = (1/N)·Σ(r − r̄)^p et σ = √m2 Pas de correction d'échantillon (Fisher-Pearson ajusté) : le catalogue est cohérent en ÷N de bout en bout, et sur N ≥ 50 l'écart est négligeable. Lecture : g1 < 0 = queue à gauche (quelques grosses barres baissières parmi beaucoup de petites hausses). σ = 0 (fenêtre de rendements plate, marché figé) → null, jamais 0. Défaut N=50 : il faut du monde pour parler de forme de distribution. Warm-up (< N rendements, donc < N+1 barres) → null.
How to read it
- Read the sign before the magnitude: it identifies which tail is doing the heavy work over the window.
- Values near zero describe a window whose up and down returns are of comparable shape, which is the ordinary case.
- A sustained negative reading means that over that window, declines arrived in larger individual steps than advances did, regardless of whether the market ended higher or lower.
- Because the deviations are cubed, one extreme bar can dominate the value; when the line jumps, find the bar that caused it before treating it as a change of character.
- Expect the value to revert once that bar leaves the window — the reversion is arithmetic, not a market event.
Parameters and defaults
Period defaults to 50 returns and accepts 3 to 1000. Small windows are dominated by individual bars and produce erratic readings that describe noise rather than shape. Longer windows characterise a regime and change slowly, so a genuine shift in asymmetry shows up late.
| Parameter | Type | Default | Range |
|---|---|---|---|
| Period | number | 50 | 3 – 1000 |
What it does not show
Skewness describes a closed window of past returns and carries no forecast. Cubing the deviations makes it acutely sensitive to single outliers, including bad prints and feed gaps, which can move the line without any real asymmetry in the market. It says nothing about the size of moves — that is what standard deviation and realized volatility measure. The inputs are closes only: volume and aggressor side never enter it. A window with no return dispersion at all produces no value.
Using it in Senzoukria
Add it from the Indicators panel of any footprint chart or candle chart. It runs on futures data from Rithmic or Databento and on crypto pairs from Binance and Bybit, on the same engine — the calculation does not change with the venue, only the data feeding it does. Market data subscriptions are billed by the provider, separately from the app.
Related indicators
- True Range — Volatility
- Std Dev — Volatility
- Squeeze — Volatility
- Chaikin Volatility — Volatility
- Realized Vol — Volatility
- Kurtosis — Volatility
See the full indicator library, or start with the order flow guide if you are new to reading aggression, delta and absorption.
Frequently asked questions
- What does negative skewness mean for a market?
- Negative skewness means the return distribution over the measured window has a longer left tail: the typical bar is small, and the large individual moves are on the downside. It describes the shape of what has already happened and does not predict the next move.
- How many bars do you need to calculate skewness?
- Mathematically three returns suffice, but the result is then driven almost entirely by one observation. The default here is 50 returns, which needs 51 bars, because a standardised third moment on a small sample is unstable and reads as noise.
- Is skewness the same as volatility?
- No. Volatility measures how far returns spread out; skewness measures whether that spread is lopsided. Two instruments can share an identical standard deviation while one delivers its movement in symmetrical steps and the other in small advances punctuated by large drops.