Large-N and Large-T Properties of Panel Data Estimators and the Hausman Test



N ∑E D⅛∑(x1≠


Exι,it)


i
1 ,, „    ,,2       „

N IID1TIl supE


t

T X (x1,it - Ex1,it)
t


2

0,


(59)


where the last convergence result holds by Lemma 15(a). Similarly, by Lemma
15(b),


EN X D2kT T X (x2k,it - Ex2k,it)


it


1 sup E —= X (x2k,it — Ex2k,it)
N
i,t     T T t


for k = 1, 2. Finally, by Lemma 15(d), we have


11

e N∑D3TXC


x3k,it


EFzi x3k,it)


N suτp -TD3kτ


E -T X(x3k.it
t T t


2

0,


(60)


EFzi x3k,it)


0,


(61)

for k = 1, 2, 3. The results (59), (60) and (61) imply that I3,νtp 0.
Proof of (51): Notice that by (48) and (50),

^N X I1,i,NT^ 13,NT


^N X I2,i,NT^ i3,nt


2

N X Iι,i,NT   III3,NT∣∣2 = Op (1) Op (1) ;

i

2

N X I2,i,NT   ∣∣I3,NTIl2 = op (1) op (1) .

i

Thus, as (Ν,T →∞) ,

^N X I1,i,NT^ 13,NT,


^NF X I2,i,NT^ 13,NT p 0.

We now consider the (k,l)th term of N Pi I1,i,NTI'0iNT. By the Cauchy-
Schwarz inequality,

(N X


I1,i,NT 12 ,i,NT


k,l


(N X[(I1,i,NT)k]2^ (N X[(I2,i,NT)ι]2


42




More intriguing information

1. The name is absent
2. Lumpy Investment, Sectoral Propagation, and Business Cycles
3. The name is absent
4. An Interview with Thomas J. Sargent
5. Urban Green Space Policies: Performance and Success Conditions in European Cities
6. Confusion and Reinforcement Learning in Experimental Public Goods Games
7. Deprivation Analysis in Declining Inner City Residential Areas: A Case Study From Izmir, Turkey.
8. Wirtschaftslage und Reformprozesse in Estland, Lettland, und Litauen: Bericht 2001
9. The name is absent
10. Migration and Technological Change in Rural Households: Complements or Substitutes?