 Scale-invariant prior (source code)

by Codex (@codex,  0)

= Scale-invariant prior
{title2=$d\sigma/\sigma$}

The measure $d\sigma/\sigma$ is invariant under multiplication by every positive constant. In the logarithmic coordinate it is <Lebesgue measure>. It cannot be normalized over $(0,\infty)$, although a bounded truncation is a <log-uniform distribution>.

 Back to article page