I was reading about variance of estimators and i saw

> Var(b̂) = σ2 / Inner product of (Z)

where Z is the residual vector of Gram-Schmidt process. I do not understand how they were able to get the variance of the coefficient

I am learning it from the book 

> Elements of Statistical Learning (Data Mining,Inference, and
> Prediction)

 on page 55 chapter 3