Skip to main content
aifinhub
Risk & Portfolio Construction Calculator Guide

How to use Returns Distribution Analyzer

Paste a returns CSV. The page renders a histogram with normal-overlay, QQ plot, skewness, excess kurtosis, the Jarque-Bera test, and a tail-weight index — the visual case for why Sharpe alone misleads on non-Gaussian returns.

By Orbyd Editorial · AI Fin Hub Team

What It Does

Use the calculator with intent

Paste a returns CSV. The page renders a histogram with normal-overlay, QQ plot, skewness, excess kurtosis, the Jarque-Bera test, and a tail-weight index — the visual case for why Sharpe alone misleads on non-Gaussian returns.

Quants who suspect the returns distribution has fatter tails than Gaussian and need the visual evidence before tear-sheet review.

Interpreting Results

QQ plot is the headline. Heavy tails show as deviation from the diagonal at both ends. Jarque-Bera p-value below 0.05 means the return distribution is statistically non-normal — Sharpe and VaR assumptions need adjustment.

Input Steps

Field by field

  1. 1

    Upload data

    Upload a return series (daily, weekly, or monthly returns).

  2. 2

    Read outputs

    Read the four moments: mean, std, skew, excess kurtosis. Excess kurtosis above 3 = fat tails.

  3. 3

    Read outputs

    Read the distribution-fit comparison (Normal vs. Student-t vs. Skewed-t vs. GED). Student-t with low ν typically wins for return series.

  4. 4

    Read outputs

    Read VaR and CVaR at 95% and 99%. CVaR > VaR by definition; the gap shows tail severity.

  5. 5

    Use result

    Use the QQ plot to spot tail behavior visually. Heavy upper-right tail = positive skew; heavy lower-left tail = negative skew.

Common Scenarios

Use realistic starting points

Trend-following daily returns

Frequency

daily

Span

5 years

Right-skewed, occasional very large positive days. Sharpe undersells this kind of distribution; Sortino captures it better.

Short-vol strategy daily returns

Frequency

daily

Span

3 years

Negative skew, fat left tail. Sharpe oversells this kind of distribution; tail-risk metrics (CVaR) tell the real story.

Try These Tools

Run the numbers next

FAQ

Questions people ask next

The short answers readers usually want after the first pass.

First four moments (mean, std, skew, kurtosis), goodness-of-fit to standard distributions (Normal, Student-t, Skewed-t, GED), tail statistics (VaR, CVaR at 95% and 99%), and visual diagnostics (QQ plot, density vs. fit). The methodology page documents each.

Related Content

Keep the topic connected

Planning estimates only — not financial, tax, or investment advice.