0
$\begingroup$

If I simply run a Lasso with y as dependent, x1,x2 as interesting and x3,x4,x5 as "choose from". Does Lasso automatically split my data up into training and validation sets? I've never really understood if that is what it's doing or not because I've seen people manually doing this beforehand in some tutorials.

$\endgroup$
4
  • $\begingroup$ What your program does, exactly, depends on your software. You have to look in the manual. I think this is a Stata question. $\endgroup$
    – Peter Flom
    Jan 13 '20 at 13:03
  • $\begingroup$ Unfortunately can't find any information on this in the manual. Would I ask this question again under "stata" tag? $\endgroup$
    – Paze
    Jan 13 '20 at 19:26
  • $\begingroup$ No, questions about software are off topic here, sorry $\endgroup$
    – Peter Flom
    Jan 13 '20 at 20:15
  • $\begingroup$ Thank you for clarifying, I have had similar questions closed under the stata tag before and was confused. I'll find a different platform to ask these types of questions. $\endgroup$
    – Paze
    Jan 13 '20 at 20:39
2
$\begingroup$

I'm a little confused about what you mean. Lasso is a specific type of regression algorithm that given some input, produces output predictions. It has nothing to do with splitting data — you have to do that manually.

$\endgroup$
2
  • $\begingroup$ Then what do cross-validation folds do, if not split the data? $\endgroup$
    – Paze
    Jan 12 '20 at 10:00
  • $\begingroup$ Cross validation is a specific technique that is distinct from your model. That splits the data. Of course, you can use Lasso regression WITH cross validation. This is good for 1) checking generalization error and 2) comparing performance with similar models. $\endgroup$
    – tchainzzz
    Jan 12 '20 at 20:12

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