1
$\begingroup$

Orange3 contains a number of regression widgets, but they all seem to be univariable i.e. one independent variable that correlates to one dependent variable. When I have more independent variables that might influence a dependent variable, how to handle this in Orange3?

$\endgroup$
  • $\begingroup$ Do you want to do this in Orange??? Seems to me that there's a lot better tools out there that will let you modify and maintain your data for the long term in a much better way. $\endgroup$ – I_Play_With_Data Oct 16 '18 at 19:33
  • $\begingroup$ Hi @I_Play_With_Data : Can you please mention names of some of such free tools . Orange comes free with anaconda and is really handy. But it would be great to use other tools which are powerful and opensource. $\endgroup$ – Sandeep Bhutani Sep 17 '19 at 16:00
  • $\begingroup$ You got Orange by getting Anaconda. Anaconda is Python for data science. You have all sorts of Python functions for statistics in statsmodels, scipy.stats, and sklearn. $\endgroup$ – Dave May 29 at 16:05
0
$\begingroup$

The regression models are multivariable. You can go to the training videos of Orange to learn how to do regression.

| improve this answer | |
$\endgroup$
0
$\begingroup$

I found out how to do multivariable linear regression in Orange. The trick is feeding the linear regression widget with the right features (4 in this case, see picture) and target variable and then getting the regression formula/coefficients out using a data widget, see screenshot.

(in thi

| improve this answer | |
$\endgroup$

Your Answer

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

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