Index: The Book of Statistical ProofsModel Selection ▷ Bayesian model selection ▷ Log model evidence ▷ Definition

Definition: Let $m$ be a generative model with likelihood function $p(y \vert \theta, m)$ and prior distribution $p(\theta \vert m)$. Then, the log model evidence (LME) of this model is defined as the logarithm of the marginal likelihood:

\[\label{eq:LME} \mathrm{LME}(m) = \log p(y|m) \; .\]
 
Sources:

Metadata: ID: D26 | shortcut: lme | author: JoramSoch | date: 2020-02-25, 12:56.