Statistics - Deviance

Table of Contents

1 - About

The deviance is negative two times the maximized log-likelihood.

And in the case of least squares regression, the deviance and the residual sum of squares are equivalent but for other model types the deviance is really just a generalization of residual sum of squares.

data_mining/deviance.txt · Last modified: 2014/04/13 21:32 by gerardnico