[R] Running SVM {e1071}

[David Meyer]

>  
> Dear David, Dear Friends,
>  
> After any running svm I receive different results of Error estimation
> of 'svm' using 10-fold cross validation. 

using tune.svm(), or the `cross' parameter of svm()?

> What is the reason ? It is caused by the algorithm, libsvm , e1071 or
> something els? 

The splits are chosen randomly.

> Which value can be optimal one? 

The Bayes Error.

> How much run can reach to the optimality.

What do you mean by `How much run'?

> And finally, what is difference between Error estimation of svm using
> 10-fold cross validation and MSE ( Mean Square Error ) ?

the former is an error estimation _procedure_, the latter is an error
_measure.

Cheers,
David