Repeated Trials

We could instead define a misfit function as our QoI instead.

This effectively turns our QoI into a scalar-valued map. \(\newcommand{\lam}{(\lambda)}\) \(\newcommand{\qoi}{Q\lam}\) $$\qoi = \frac{1}{M} \sum_{i=1}^M \left(\frac{O_i\lam-d_i}{\sigma_i}\right)^2$$

This represents our average deviation from the data.


What are the differences?