Hyperparameters for the EM algorithm.
Objects can be created by calls of the form
...). In addition, named lists can be coerced to
objects, names are completed if unique (see examples).
Maximum number of iterations.
Minimum prior probability of clusters, components falling below this threshold are removed during the iteration.
The EM algorithm is stopped when the
(relative) change of log-likelihood is smaller than
If a positive integer, then the
log-likelihood is reported every
verbose iterations. If 0,
no output is generated during model fitting.
Character string, one of
"random" or (
Reports the number of random initializations
stepFlexmix() to determine the mixture.
new("FLXcontrol") to see the default settings of all slots.
Friedrich Leisch and Bettina Gruen
1 2 3 4 5 6