X-Validation - how is the division of examples done

miaquemiaque MemberPosts:4Contributor I
edited November 2018 inHelp
Hello,
I have a question. How are the examples divided when using X-Validation?

For example, when I use X-Validation with 4 iteriations on the data of 100 examples, does it mean that

- first 75 examples will be for the learning purpose and the next 25 for testing in the 1 iteriation, then 1-25 and 51-100 will be for learning and 26-50 for testing... etc. OR

- the set for learning will be each time 75 and for testing 25, but examples in sets are chosen randomly?

Thank you in advance
Tagged:

Answers

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University ProfessorPosts:3,371RM Data Scientist
    the first one.

    the second one is similar to Bootstrap validation. But in Bootstrap validation you can have examples twice in the training set.

    ~Martin
    - Head of Data Science Services at RapidMiner -
    Dortmund, Germany
Sign InorRegisterto comment.