layout |
mathjax |
author |
affiliation |
e_mail |
date |
title |
chapter |
section |
topic |
theorem |
sources |
proof_id |
shortcut |
username |
proof |
true |
Joram Soch |
BCCN Berlin |
joram.soch@bccn-berlin.de |
2022-10-20 03:11:00 -0700 |
Derivation of the model evidence |
Model Selection |
Bayesian model selection |
Model evidence |
Derivation |
|
P367 |
me-der |
JoramSoch |
Theorem: Let $p(y \vert \theta,m)$ be a likelihood function of a generative model $m$ for making inferences on model parameters $\theta$ given measured data $y$. Moreover, let $p(\theta \vert m)$ be a prior distribution on model parameters $\theta$ in the parameter space $\Theta$. Then, the model evidence (ME) can be expressed in terms of likelihood and prior as
$$ \label{eq:ME-marg}
\mathrm{ME}(m) = \int_{\Theta} p(y|\theta,m) , p(\theta|m) , \mathrm{d}\theta ; .
$$
Proof: This a consequence of the law of marginal probability for continuous variables
$$ \label{eq:prob-marg}
p(y|m) = \int_{\Theta} p(y,\theta|m) , \mathrm{d}\theta
$$
and the law of conditional probability according to which
$$ \label{eq:prob-cond}
p(y,\theta|m) = p(y|\theta,m) , p(\theta|m) ; .
$$
Plugging \eqref{eq:prob-cond} into \eqref{eq:prob-marg}, we obtain:
$$ \label{eq:ME-marg-qed}
\mathrm{ME}(m) = p(y|m) = \int_{\Theta} p(y|\theta,m) , p(\theta|m) , \mathrm{d}\theta ; .
$$