Bayesian Model Architect
Kruschke diagrams Β· McElreath notation Β· Guided model building Β· brms export
Β© Dr. Rainer DΓΌsing Β· Interactive Tools by Claude
1 Likelihood β€” Which distribution?
2 Variables
Predictors
3 Structure
Name of the group index variable in the dataset (e.g. j = schools, person = subjects)
4 Priors
5 Detail level
Model diagram (Kruschke notation)
Ξ± Ξ² Οƒ Hyperprior y Plate β—‹ latent   β–‘ observed
McElreath Notation
β€” click on a node β€”
What is this?
Why this prior?
Tip
β„Ή Bayesian Model Architect
Reading and understanding Kruschke diagrams

This tool shows you the graphical model structure of Bayesian regression models β€” live, interactive, in simple examples:

Β· β—‹ open circles = unknown parameters that need priors (Ξ±, Ξ², Οƒ)
Β· β–‘ rectangle = observed data y
Β· β€’ dot = deterministic node (ΞΌα΅’) β€” no prior, computed from inputs
Β· Arrows show the generative direction: Prior β†’ Parameter β†’ Data
Β· Plates (dashed frames) mark repeated units (i = 1…N observations; j = 1…J groups)

In the hierarchical model, each group j receives a deviation from the global intercept: uβ‚€β±Ό ~ Normal(0, Ο„β‚€). Ο„β‚€ controls the degree of partial pooling β€” small Ο„β‚€ = strong shrinkage. In McElreath (Ch. 14, p. 441 ff.) this parameter is called Οƒ_Ξ±. Random Slopes (u₁ⱼ ~ Normal(0, τ₁), corresponding to McElreath's Οƒ_Ξ²) are implemented here only for the first predictor, to illustrate the diagram principle.
Simple example models only: up to 4 predictors, one group structure, 5 likelihoods. The focus is on structure, not full model complexity. Click on any node in the diagram for an explanation.
πŸ“– Guide β€” Step-by-step (top). Recommendation: read through first!
πŸ’‘ Explanations β€” Click on nodes or formula rows on the right for context on each parameter.
⬑ Golem light β€” Generates R code: draw parameters from priors and simulate data.
For the full model scope:
⬑ brms Model Builder β€” 15 likelihoods, polynomials, interactions, distributional parameters, random effects, prior predictive check β€” directly executable brms code.

β†’ brms Model Builder β†—