FAQ - Frequently Asked Questions
Issue:
-
How do I choose between the different cross-validation leave-out options?
Possible Solutions:
-
There are many attributes that influence selection of the appropriate cross-validation scheme for a given situation:
* The ordering of the samples in the dataset,
* The total number of objects (and variables) in the dataset
* The presence (or lack thereof) of replicate samples in the dataset
* The specific objective(s) of the analysis,
* The consequences/costs of overly optimistic or overly pessimistic results, and
* The amount of time available to do cross-validation
For details on the different methods, see our Wiki page: Using Cross-Validation
and, in particular, Choosing the Cross-Validation Method
Keywords: cross validation, leave out methods
Still having problems? Check our documentation Wiki or try writing our helpdesk at helpdesk@eigenvector.com
