I have used SPSS Clementine in order to train a classifier, for this I have used a partition node with 2 parts(train and test),then using a c5-tree and cross-fold validation.

I did this because I think SPSS separates training data and does a 10-fold validation to build a best model and then test it by test data. would you please verify or criticize this?

this is the explanation of SPSS about how cross-fold works: "Cross-validate. If this option is selected, C5.0 will use a set of models built on subsets of the training data to estimate the accuracy of a model built on the full dataset. This is useful if your dataset is too small to split into traditional training and testing sets. The cross-validation models are discarded after the accuracy estimate is calculated. You can specify the number of folds, or the number of models used for cross-validation."

And if my idea is not true(to use both partitions and cross-validation) what has happened in SPSS? Is there any priority or not?

thanks all

  • $\begingroup$ I am not totally clear from your question however it is likely that SPSS automatically decides which partitions to use for each run of Cross-validation and so you do not need to partition beforehand. $\endgroup$ – BGreene Feb 17 '14 at 12:36
  • $\begingroup$ thanks.so do you know what does it do with partitions(I didn't know this so I have used partitioning)?I mean does it ignore them or I should repeat my long experience all again?? $\endgroup$ – airam Feb 18 '14 at 2:16

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.