Weighted least square seems to be a special case of Generalized Least Square. If we have generalized least square technique why do we need to apply weighted least square? or do we call them interchangeably?

  • $\begingroup$ well, weighted least squares is much simpler to implement ... $\endgroup$ – kjetil b halvorsen Mar 10 '17 at 13:21
  • $\begingroup$ So what's the difference? $\endgroup$ – SmallChess Mar 10 '17 at 14:19
  • 1
    $\begingroup$ Both generalized and weighted LS weights using a matrix of weights $W$. For generalized LS this is a general (symmetric) matrix, for weighted LS it is diagonal. $\endgroup$ – kjetil b halvorsen Oct 12 '17 at 2:38

When the errors are dependent,we can use generalized least squares (GLS). When the errors are independent, but not identically distributed, we can use weighted least squares (WLS), which is a special case of GLS.

| cite | improve this answer | |

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.