In order to prove asymptotic normality of the time series OLS estimator (this context is not important), I have done the following:
Assumptions:
• var(yt)=γ0∀t
• cov(yt,yt−j)=γj∈Rk∀j
• limj→∞cov(yt,yt−j)=γj=0
• ∑|γj|<∞
Then:
L=limT→∞var(√T(T−1∑tyt−μ))=limT→∞var(T−1/2∑tyt)=limT→∞T−1var(∑tyt)=limT→∞T−1∑t∑scov(yt,ys)=limT→∞T−1[T⋅γ0+2⋅(T−1)⋅γ1+2⋅(T−2)⋅γ2+...+2⋅γT−1]=limT→∞T−1[Tγ0+2∑1≤j≤T−1(T−j)γj]=limT→∞γ0+2∑1≤j≤T−1(1−jT)γj I'm assuming the last step equals: γ0+2∑∞j=1γj
since concluding from here is rather easy. The problem being that I do not think it's the case, since j also converges to infinity.
Am I wrong? If so, why?
No comments:
Post a Comment