Hi!
I am currently learning about unit root processes (eg random walks) in my class.
I am having trouble understanding how to define the scaling matrix for the rate of convergence of the regression coefficients in a regression w/ a constant term on a nonstationary random walk (equation 2).
I am confused how the order rates of convergence was identified in the matrix form of the OLS statistics in the last equation (labeled 26). Obviously the element $(1,1)$ in $(X'X)^{-1}$ converges at rate $n$ but how do you know the rate of convergence for the other terms?
-Thank you!