I make a comparison on ridge regression and OLS using simulation.

As i set my correlation as 0.9, which is high, i expect the standard error of ridge regression to be low. However, it is not. Different on the coefficient of the ridge regression, it is always lower than OLS. Why does the standard error does not becoming lower than OLS? Don't the coefficient affect the standard error?

I am using R to make my simulation.

  • $\begingroup$ Please post your R code. $\endgroup$ – Chechy Levas Dec 23 '18 at 5:49
  • $\begingroup$ I had post it, please help @ChechyLevas $\endgroup$ – ANA Dec 23 '18 at 6:02
  • $\begingroup$ As far as I know ridge regression is performed on normalized (mean 0 sd 1) variables. I don't see any such normalization in your code. Did you do this earlier in the code? $\endgroup$ – Chechy Levas Dec 23 '18 at 12:36

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.