Return Distribution Analyzer
Summarize ordered equal-frequency returns with NIST population moments and an explicit N plus one percentile convention, including quartiles, skewness and kurtosis.
Enter observed equal-frequency returns
Use signed percentage returns from one consistent sampling and net-or-gross convention. Order is retained as entered, while percentile ranks use an ascending copy.
Enter percentage numbers without percent signs. Separate with spaces, commas, semicolons or new lines. Maximum 500.
Entered return distribution arithmetic
Entered Strategy Diagnostics 1.0.0.
| Rank | Ordered return | N plus one plotting position |
|---|
How the return distribution is summarized
Kurtosis = (Σ(Y[i] − Ȳ)⁴ ÷ N) ÷ σ⁴
Percentile position = p(N + 1), linearly interpolated
Version 1.0.0 follows the NIST unadjusted Fisher-Pearson skewness and original kurtosis definitions. Their standard deviation uses N in the denominator; excess kurtosis is also shown as original kurtosis minus three.
Percentiles use the NIST p times N plus one rank with linear interpolation between adjacent ordered observations. Positions beyond the available endpoints are clipped to the entered minimum or maximum.
Assumptions and limits
- Enter 4 to 500 signed percentage returns under one consistent sampling convention.
- A constant series is rejected because standardized shape moments divide by zero spread.
- Different software may use adjusted skewness, excess-only kurtosis or another percentile definition.
- Extreme observations can materially change the mean, standard deviation, skewness and kurtosis.
- No normality, tail-risk forecast, expected shortfall, strategy grade or recommendation is produced.
Worked example from the audited fixture
For the audited 30-return fixture, the mean is 0.110000%, the median is 0.150000%, the minimum is −1.200000% and the maximum is 1.500000%.
IQR = 1.425000%; population standard deviation = 0.770000%
Skewness = 0.097500; kurtosis = 1.822869; excess kurtosis = −1.177131
How to interpret the result
The percentiles use the disclosed p(N + 1) interpolation, while skewness and kurtosis use population moments with N in the denominator. The small positive skew and below-three kurtosis describe only these 30 values; they do not prove a distribution or predict tail losses.
Frequently asked questions
- Enter 4 to 500 non-identical signed percentage returns under one consistent sampling and net-or-gross convention.
- Version 1.0.0 uses the NIST unadjusted Fisher-Pearson population-moment formula with N-divisor standard deviation.
- The fourth population central moment is divided by population standard deviation to the fourth power.
- The original NIST convention has a normal reference of three; excess kurtosis subtracts three and therefore has a normal reference of zero.
- The page uses the NIST p times N plus one rank, linear interpolation and disclosed clipping at the entered endpoints.
- Standardized shape moments divide by zero spread, so the calculation is rejected.
- Programs may use adjusted skewness, excess-only kurtosis or another percentile rank and interpolation convention.
- No. It describes the entered sample and does not prove normality, forecast losses, validate a strategy or make a recommendation.
Sources and methodology
- NIST/SEMATECH — Measures of Skewness and Kurtosis — Published population-moment formulas and convention warnings.
- NIST/SEMATECH — Percentiles — Published order-statistic and p times N plus one interpolation convention.
Continue return review
Compare the trading records behind your sample
Keep one broker account, return convention, fee treatment and sampling rule across the entered observations before comparing arithmetic.
FXOpen
Confirm account statements and trading conditions behind the entered sample.
Check FXOpen termsRisk and affiliate disclosure: Leveraged forex and CFD trading can result in substantial losses. These are affiliate links, so ForexMT4Indicators.com may receive compensation if you register or trade through them, at no additional cost to you. Availability and terms vary by jurisdiction and broker entity.

