Assumption turned into performance validation.
Great post as usual, Avi. I enjoy reading all your "daily dose" posts.
I just want to comment that it seems that the link to the Jupyter notebook is broken...Thanks for sharing your knowledge! Please, keep going.
Unbiasedness and minimal variance of a linear regression model has nothing to do with normality of residuals. It only gives you another way to derive parameters using MLE and makes your hypotheses tests valid.
Great post as usual, Avi. I enjoy reading all your "daily dose" posts.
I just want to comment that it seems that the link to the Jupyter notebook is broken...Thanks for sharing your knowledge! Please, keep going.
Unbiasedness and minimal variance of a linear regression model has nothing to do with normality of residuals. It only gives you another way to derive parameters using MLE and makes your hypotheses tests valid.