HDclassif version 1.2 2012-01-05:
- the citation of the package is updated
- new reference in .Rd files

HDclassif version 1.2 2011-07-15:

- now the BIC an the log likelihood are not divided by N (the number of observation) anymore
- help files have been rewritten
- very slight changes in the random initialization of hddc (now the random init cannot begin with an empty class)
- changes on the predict.hdc function. It now works all the time.
- added some features to hdda, notably the model "all" and the V-fold cross validation for dimension selection
- a cross-validation option has been added for \var{hdda} in order to select the best dimension or threshold with respect to the CV result
- big changes in the function plot.hdc. Now the dimensions selection using either Cattell's scree-test or the BIC can be plotted.
- the graph of the eigenvalues has been removed
- graph scale changed for Cattell's scree-test to see directly the threshold levels
- adding the possibility to choose the dimension with the "bic" criterion in \var{hddc}
- added some warnings when the value of the parameter b is very low (inferior to 10e-6)
- the calclulation trick when N<p is now done since Ni<p, Ni being the number of observations for the class i
- added a leave-one-out cross-validation option to hdda


HDclassif version 1.1.3 2011-03-30:

- fixed a bug: hddc can now be initialized with a given class vector 


HDclassif version 1.1.2 2011-02-10:

-slight change in the demo functions
-changing description
-Now zip.data=no


HDclassif version 1.1.1 2010-12-01:

-the models can now be selected using integers instead of names
-the graph of hddc now gives the comparison between different models and different number of clusters
-the calculation of the log likelihood has been modified in hddc


HDclassif version 1.1 2010-10-01:

-A plot minor issue is fixed
-Some names are changed in the functions hdda and hddc : 
	¤ Former name	->	New name
	¤ AkiBkQkDk		->	AkjBkQkDk
	¤ AkiBQkDk		->	AkjBQkDk
	¤ AkiBkQkD		->	AkjBkQkD
	¤ AkiBQkD		->	AkjBQkD
	¤ AiBQD			->	AjBQD
-When several models are given, HDDA and HDDC now explicitly give the model they select
-The initialization kmeans can be settled by the user using ... in HDDC
-HDDC now handles several model at once
-A demo has been built for the methods hdda and hddc