powered by
ClusterAlgo
There is three algorithms and two stopping rules possibles for an algorithm.
Algorithms:
EM: The Expectation Maximisation algorithm
EM
CEM: The Classification EM algorithm
CEM
SEM: The Stochastic EM algorithm
SEM
SemiSEM: The Semi-Stochastic EM algorithm
SemiSEM
Stopping rules:
nbIteration: Set the maximum number of iterations
nbIteration
epsilon: Set relative increase of the log-likelihood criterion
epsilon
Default values are \(200\) nbIteration of EM with an epsilon value of \(1.e-8\).
The epsilon value is not used when the algorithm is "SEM" or "SemiSEM".
clusterAlgo(algo = "EM", nbIteration = 200, epsilon = 1e-07)
a [ClusterAlgo] object
character string with the estimation algorithm. Possible values are "EM", "SEM", "CEM", "SemiSEM". Default value is "EM".
Integer defining the maximal number of iterations. Default value is 200.
Real defining the epsilon value for the algorithm. Not used by the "SEM" and "SemiSEM" algorithms. Default value is 1.e-7.
Serge Iovleff
clusterAlgo() clusterAlgo(algo="SEM", nbIteration=50) clusterAlgo(algo="CEM", epsilon = 1e-06)
Run the code above in your browser using DataLab