Distribution Lab
Normal Β· Gamma Β· Beta Β· Poisson Β· Binomial Β· GLM preparation
Β© Dr. Rainer DΓΌsing Β· Interactive Tools by Claude
Distribution Lab β€” Explore probability distributions interactively.  Β·  28 distributions Β· Adjust parameters Β· Show moments Β· brms roles & parametrisation Β· Lockable x-axis Β· Ordinal models
Normal
Y ~ Normal(ΞΌ, Οƒ)
Parameters
Show moments
Key figures
Relationships between distributions
LEGEND: Limit / special case Constructed from Cross-group relationship βŠ• Convolution (sum of two random variables) CONTINUOUS UNBOUNDED Cauchy Cauchy(ΞΌ, Οƒ) Student-t Student-t(Ξ½, ΞΌ, Οƒ) Normal Normal(ΞΌ, Οƒ) Skew-Normal Skew-Normal(ΞΎ, Ο‰, Ξ±) Ξ½ = 1 Ξ½ β†’ ∞ Ξ± = 0 (selectable in Prior Lab) CONTINUOUS POSITIVE Exponential Exponential(Ξ») Gamma Gamma(Ξ±, Ξ²) Log-Normal LogNormal(ΞΌ, Οƒ) ExGaussian ExGauss(ΞΌ, Οƒ, Ξ²) = Normal(ΞΌ,Οƒ) βŠ• Exponential(Ξ²) Ξ± = 1 Inv. Gaussian InvGaussian(ΞΌ, Ξ») ChiΒ² χ²(k) F-Distribution F(d₁, dβ‚‚) Shifted LogNormal ShiftedLogNormal(ΞΌ,Οƒ,Ξ΄) = Gamma(k/2, Β½) Ο‡Β²βˆ•Ο‡Β² + Ξ΄ (shift) βŠ• Exponential (cross-group) Y = exp(X) (cross-group) BOUNDED [0,1] Beta Beta(Ξ±, Ξ²) Beta(1,1) = Uniform[0,1] ZI-Beta ZI-Beta(ΞΌ, Ο†, zi) ZOIB ZOIB(ΞΌ, Ο†, zoi, coi) Bernoulli Bernoulli(p) Beta = conjugate prior for p + 0 (zi) + 1 (zoi) COUNT DATA (DISCRETE) Beta-Binomial BetaBin(n, ΞΌ, Ο†) Binomial Binomial(n, p) Poisson Poisson(Ξ») Neg. Binomial NegBin(ΞΌ, Ο†) Ο† β†’ ∞ nβ†’βˆž, pβ†’0 Ο† β†’ ∞ p ~ Beta n = 1 ORDERED CATEGORIES (ORDINAL) same latent structure, different link function (Normal ↔ Logistic) Cum. Probit OrderedProbit(Ξ·,Ο„,Ξ”,K) Cum. Logit OrderedLogit(Ξ·,Ο„,Ξ”,K) At K=2 categories β‰ˆ binary logit/probit regression (groups "Count data"/"Bounded [0,1]") Normal = limit of Student-t (Ξ½β†’βˆž), Skew-Normal (Ξ±=0), Gamma (Ξ±β†’βˆž) and Binomial (nβ†’βˆž, pβ†’0) χ²(k) = Z₁² + … + Zβ‚–Β² (Zα΅’ ~ Normal(0,1)) β€” also a special case of Gamma(k/2, Β½) Bold = reference distribution per group Β· dashed border = "constructed" distribution (ExGaussian, Shifted LogNormal) Β· faded = reference, not selectable in the Distribution Lab (Cauchy) All 21 distributions of the Distribution Lab plus Cauchy (limit of Student-t, selectable in Prior Lab) Β· Source: Ben Lambert, A Student's Guide to Bayesian Statistics (2018), p. 225
Help β€” Distribution Lab
Overview
Distribution Lab shows 28 probability distributions interactively β€” as preparation for GLMs and Bayesian models in brms. Which distribution fits which data? For each distribution: description, use cases, parameter explanation, brms usage and technical details.
Navigation
Category tabs (top) select the distribution group.
Distribution buttons below select the specific distribution.
Sliders on the left adjust parameters in real time.
Lock x-axis
X lock button (topbar): Freezes the x-axis so that when changing parameters (e.g. ΞΌ or Οƒ) the shape change is directly visible β€” instead of the axis rescaling. Resets automatically when switching distributions.
Distribution relationships
⊞ Relations button opens a large overview map with all 21 distributions of the Distribution Lab and their connections: special cases, limits, constructions. Orientation in the distribution zoo.
Moments
Mean (blue), Median (green), Mode (orange) as vertical dashed lines. Each moment independently toggleable.
brms parametrisation
For Gamma and Beta: toggle between brms (ΞΌ, Ο†) and classical (Ξ±, Ξ²). Automatic conversion. The brms parametrisation is more intuitive: you set the mean directly.

The "Usage in brms" section shows for each distribution: as likelihood (family syntax, link) and as prior (prior() syntax) β€” including typical parametrisations.
Mixed distributions
ZI-Beta and ZOIB: point masses at 0/1 as red bars, Beta component as curve. Hurdle-Gamma and Hurdle-Lognormal: point mass at 0 as a red bar, positive component as a curve on (0, ∞) instead of [0,1].
Discrete distributions
Bar chart of the PMF. Mode = tallest bar.