0
$\begingroup$

I mainly use spss modeler but I don't think it has the functionality to use a generated model to predict the group new unseen cases belong to (one of two). It seems like it would need to be done manually?

I was wondering if it's possible in R? For instance, after splitting my data into training and test, I want to create some predictive models such as random forest, logistic regression etc. using the training set and then use those generated models to predict the test data set.

I found some material online for predicting using Weka but have not used it before and can't seem to find a (safe) place to download it from. However I have only basic skills in R so if it would be better to use Weka, can someone provide me with the link to downloading the tool?

Thanks!

$\endgroup$

1 Answer 1

0
$\begingroup$

I don't use that tool, but it'd be pretty silly if a model building tool didn't have an easy mechanism to score new data. It will just be a matter of finding out how to do it in whatever tool you're most comfortable with. For SPSS I found this: Applying SPSS Models

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.