What will I learn here?
Generalised Linear Models differ in their
conditional distribution —
not every outcome variable is normally distributed. This tool shows the 3D posterior landscape
P(y | x, β₀, β₁) for six GLM families: How does the distribution shape change when
the predictor x or the parameters vary?
Recommended exploration
- Click through all six model tabs — observe how the distribution shape changes depending on the outcome type
- Vary β₁ (Slope) — how does the conditional distribution change along the x-axis?
- For Poisson: increase β₀ — the distribution shifts and widens (Variance = Mean)
- For Neg. Binomial: vary dispersion r — how does it differ from Poisson under overdispersion?
- Rotate and zoom the 3D view — explore the landscape from different angles
The six GLM families
Normal (OLS): continuous data — symmetric bell curve, σ constant
Poisson: count data (0,1,2,…) — log link, Variance = Mean
Neg. Binomial: count data with overdispersion — Variance > Mean
Gamma: positive continuous data — right-skewed, log link
Binomial: number of successes out of n trials — logit link
Logistic: binary 0/1 data — probability between 0 and 1