Gumbel Distribution Calculator

The Gumbel Distribution, also known as the Type I Extreme Value Distribution, models the distribution of the maximum (or minimum) of a number of samples of various distributions. It is widely used in hydrology for flood frequency analysis, meteorology for extreme rainfall events, and structural engineering for wind loads.

The location parameter μ (mu) represents the mode of the distribution — the value where the PDF peaks. The scale parameter β (beta) controls the spread or dispersion of the distribution. β must always be a positive number. Larger β values produce a wider, flatter distribution.

The PDF is: f(x; μ, β) = (1/β) × exp(−z − exp(−z)), where z = (x − μ) / β. The CDF is: F(x; μ, β) = exp(−exp(−z)). These formulas describe the probability density and cumulative probability at a given value X.

In hydrology, the Gumbel method estimates the return period of flood events. Historical annual maximum discharge data is fitted to a Gumbel distribution, and the location and scale parameters are estimated from the sample mean and standard deviation. This allows engineers to predict the probability of extreme events like a 100-year flood.

The mean of a Gumbel distribution is μ + β × γ, where γ ≈ 0.5772 is the Euler–Mascheroni constant. The standard deviation is (π / √6) × β ≈ 1.2825 × β. Both values are calculated and displayed by this calculator.

The Survival Function gives the probability that the random variable X exceeds a given value. It equals 1 minus the CDF. In flood analysis, this represents the exceedance probability — for example, a survival value of 0.01 indicates a 1% chance of exceeding that flood level in any given year (the 100-year return period event).

The PDF (Probability Density Function) describes the relative likelihood of the random variable taking a specific value X. The CDF (Cumulative Distribution Function) gives the probability that the variable is less than or equal to X. In other words, the CDF is the integral of the PDF up to point X.

Use the Gumbel Distribution when modeling extreme values — the maximum or minimum of a large sample. Unlike the Normal Distribution, the Gumbel is skewed to the right, making it suitable for phenomena like maximum annual rainfall, earthquake magnitudes, or peak wind speeds, where extreme outcomes are more common than a symmetric distribution would predict.