Cross Validation In R

Question: (Closed) Cross Validation In R

9.3 years ago by

Mery • 0

Mery • 0 wrote:

I want to perform regression methods such as LDA, QDA, logistic and bayesian model averaging on the Australian data in R. How can I do cross validation in R for this data ?

• 3.7k views

ADD COMMENT • link •

modified 9.3 years ago by Vladimir Chupakhin • 520 • written 9.3 years ago by Mery • 0

Do people earn points for closing questions? Cross-validation is an important topic in bioinformatics and thus questions and answers with content on cross validation are relevant to bioinformatics. The question may be asked poorly, but the answerers could fill in the gap if desired, and the questioner could be prompted for better question posing. I don't understand how cross-validation is off-topic for bioinformatics.

ADD REPLY • link written 9.3 years ago by seidel ♦ 7.2k

Sorry, "the Australian data"? I assume you mean the sample dataset, data(austres). Sounds like you're learning R and this is not a bioinformatics question.

ADD REPLY • link written 9.3 years ago by Neilfws ♦ 49k

9.3 years ago by

Chris • 1.6k

Munich

Chris • 1.6k wrote:

You split up your dataset into non-overlapping folds, e.g. randomly or stratified. This should be easily doable with R. Then you train your model on one part and test on the rest. In e.g. 10-fold CV you essentially rotate your folds, i.e. 9/10 of the set is used as train- the rest 1/10 as test set. Obviously this could be done 10 times.

ADD COMMENT • link written 9.3 years ago by Chris • 1.6k

9.3 years ago by

Vladimir Chupakhin • 520

Toledo, Spain

Vladimir Chupakhin • 520 wrote:

try caret library for R - it's include crossvalidation options by default and coupled with different learning algorithms

ADD COMMENT • link written 9.3 years ago by Vladimir Chupakhin • 520

Please log in to add an answer.

The thread is closed. No new answers may be added.

Similar posts • Search »