# Rationale for likelihood function parameter choice in Black-Litterman model?

So we are interested in a PDF for equilibrium returns given the views. Why do we choose our view means as the mean parameter and observed market covariance as the covariance parameter? Seems a bit arbitrary.

• exactly; your likelihood funciton is about $\theta$ which is the parameter set and the choice of prior $\pi(\theta)$ is what we need before making to posterior; if we say $\pi(\theta) ~ N(\xi,v)$, the simplest way to get $\xi$ is to calculate views' mean – numerairX May 16 at 16:49