I couldn't find least median square technique on python, any one knows any library? Or how to adapt it from the common linear regression.

  • $\begingroup$ Do you mean quantile regression? I think statsmodels has a quantile regression method called quantreg $\endgroup$ – Demetri Pananos Mar 5 at 15:10
  • $\begingroup$ I meant this one researchgate.net/profile/Peter-Rousseeuw/publication/… $\endgroup$ – jonny5 Mar 5 at 15:16
  • 1
    $\begingroup$ Short answers: (1) it cannot be implemented using "common linear regression" and (2) you don't want to do it, because it is so inefficient. What is your motivation for looking into this technique? We might be able to suggest better solutions. $\endgroup$ – whuber Mar 5 at 16:13
  • $\begingroup$ I've used in Weka and it was better with respect to MLP, M5R, LSTM, SMOR (behind alternating model tree - however this one is not available in Python). Please, could you suggest me others. The input data is composed of cartesian coordinates (latitude and longitud) as well the output. thank for the help $\endgroup$ – jonny5 Mar 7 at 10:33

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.