Can anyone explain to me what does Normal Approximation do over and above what is done by MAP in some easy words?
I have read enough on http://pymc-devs.github.io/pymc/modelfitting.html#normal-approximations but it is too complicated for me.
An example showing the difference will be very helpful.
MAP simply returns a posterior mode, while the NormalApproximation uses a quadratic Taylor series approximation to the posterior, and so can return both the expected value and the covariance matrix. Of course, it uses a normal distribution to approximate the posterior, which may not be appropriate.
