0
$\begingroup$

Hello I am not sure about when can I use LDA.

For example can I apply LDA with this kind of data?

  class smoke coffe trat
1   1     1    1    1
2   1     1    1    1
3   1     1    1    0
4   0     1    1    0
5   0     1    1    0

All variables are dichotomic

And if is possible, which is the best option of LDA?

Thanks

$\endgroup$
3
  • $\begingroup$ Because your predictors are not scale, normally distributed ones within classes, LDA is not a good choice. Apply logistic regression instead. $\endgroup$
    – ttnphns
    Jan 3 '20 at 11:07
  • $\begingroup$ That data is only a sample of al data, can you explain a bit more, and what you want to say with "normally distributed ones within classes"? Thanks $\endgroup$
    – Lololo
    Jan 3 '20 at 11:48
  • $\begingroup$ I would recommend you to read first about LDA, in particular about its assumptions. There are many threads on this site about it. One of the many is stats.stackexchange.com/q/95247/3277 $\endgroup$
    – ttnphns
    Jan 3 '20 at 12:05

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.