1
$\begingroup$

Could someone please explain the difference between the root mean square error and the standard error of the estimate? I have run a multiple regression in SPSS and have got a standard error of estimate value but when I do the same regression in R and ask for the RMSE I get the same value as the standard error of estimate value. They seem like the same thing to me or am I wrong?

$\endgroup$
1
  • $\begingroup$ In essence, yes, but distrust terminology unless you can check on the equations used, which should always be documented somewhere. $\endgroup$
    – Nick Cox
    Oct 10 '17 at 15:11
-1
$\begingroup$

They are not the same. The root mean square error (RMSE) represents the average distance between predicted values and actual values while the residual standard error represents the standard deviation of the residual values, i.e. it gives us an idea of how much-projected value could vary from the mean of the actual value.

$\endgroup$
2
  • $\begingroup$ You might want to research this a little more ... $\endgroup$ Dec 22 '20 at 14:41
  • $\begingroup$ -1 The “average” you describe is the mean absolute error, which is not equal to the RMSE. $\endgroup$
    – Dave
    Jan 23 at 17:13

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.