penalty_BirgeMassart_shape2
is the penalty shape defined by :
pen_shape = C*K_try + log(model_complexity).
It dominates the penalty defined by penalty_BirgeMassart_shape1
.
penalty_BirgeMassart_shape2(K, p, model_complexity, C = 2.5)
value of the penalty.
the number of shifts
the dimension of the data
the complexity of the set of models with dimension K.
a non-negative constant. Default is 2.5 (as suggested in Lebarbier 2005)
See Birgé Massart (2001). Must be applied to least-square criterion. This penalty should be calibrated using the slope heuristic.
penalty_BirgeMassart_shape1
,
penalty_BaraudGiraudHuet_likelihood