B3 - C0
μθT A1+A3) C
-1
× (B4 + B5) - C0 μθ2A1 + A3) μθ2^A2 + (A4 + A5))
. (94)
Part (a)
Notice that
C0
μθTA1+A3) C
C0Dx,T Tθ2p √T∙X-T'Gx,TA1Gx,τ Jχ,T√t + Dx,TA3Dχ,Tj
1
Dx,T C
Tθ2T(C0Dx,T
-1Gx,TA1Gx,T
+ j√t Dx,T A3Dx,τJ⅛
-1
x,T
1 JxT1
√T (Dχ,τC)
Jx,T2
Op I τ I = op(1).
The third equality holds because the limit of Gx,TA1Gx,T is positive definite
(by Lemma 2(a) and Assumption 12), Tθ2T = O(1), and
Dx,T C, Gx,TA1Gx,T,Dx,TA3Dx,T = Op (1)
(by Lemma 2(a), (c)). The last equality results from the fact that
J -T1
√J = o (1).
Thus, as (N, T →∞) , the denominator of (94) is
B3 - C0
(⅛ A1+A3)
-1
C=B3+op(1).
(95)
Next, under both the random effects assumption (Assumption 9) and the
local alternatives (Assumption 11), it follows from Lemmas 2 and 3 that the
second term in the numerator of (94) is
C0 μθ2Ai+A3) μθ2√NA2+√N (A4+A5))
-1
C0Dχ,τ Tθθ2√√TJχ,τGχ,τAiGχ,τ Jχ,τ√T + Dχ,τA3Dχ,τ^
× TTJ jχ,τ√NTGxτA2 + √NDχ,τ (A4 + A5)^
58