A parametric approach to the estimation of cointegration vectors in panel data



Appendix A

Proof of Theorem 1

First assume that αi and Σi are known so that zit = (αi0Σi-1αi)-1α0iΣi-1yit
and zi+t = zit - yi(,1t)-1 .

From Johansen (1991) it is known that in a cointegrated VAR(1) model
we have
t

yit = β (αi0,β)-1α0i,     εis + uit ,

s=1

where uit is (asymptotically) stationary. From T -1/2 Pts=1 εis = T -1/2 P[ta=T1] εit
Bi (a), where Bi(a) Bi is a Brownian motion with covariance matrix Σi. It
follows that

T

BiBi0  αi, (β0 αi,)-1β0


T - X yityi0t β(α0i,β)- α0i,
t=1

Using E(f BiBi) = (1 /2)∑i we obtain

1
NT2


NT

XXyi(,2t)-1yi(,2t)-10
i=1 t=1


p

-→


-⅛ .

2 2


Furthermore,

t-1

εisvi0t

s=1


yi(,2t)-1 vi0t  =  β2,(α0i,β)-1α0i,

where vi0t = (α0iΣi-1αi)-1α0iΣi-1εit. Since εi,t-j is independent of vit for j 1
we have

1∙        1 p

lιm —EB

T,N→∞ NT2


NT

ΣΣvec(yi(,2t)-1vi0t)vec(yi(,2t)-1vi0t)0

i=1 t=1

= lim E

T,N→∞


1

NT2


NT

XXyi(,2t)-1yi(,2t)-10
i=1 t=1

NT

NT ΣΣ Vitvit
i
=1 t=1

= (1 /2)Ω2 ®υ

and, therefore,

NT

^ N(0,2 Θυ) .


T7N ∑∑*c ( B -1 V0t )

T N i=1 t=1

15



More intriguing information

1. IMPLICATIONS OF CHANGING AID PROGRAMS TO U.S. AGRICULTURE
2. Ruptures in the probability scale. Calculation of ruptures’ values
3. A Hybrid Neural Network and Virtual Reality System for Spatial Language Processing
4. Multimedia as a Cognitive Tool
5. Policy Formulation, Implementation and Feedback in EU Merger Control
6. The Making of Cultural Policy: A European Perspective
7. EXECUTIVE SUMMARIES
8. The Impact of Financial Openness on Economic Integration: Evidence from the Europe and the Cis
9. Achieving the MDGs – A Note
10. AGRICULTURAL PRODUCERS' WILLINGNESS TO PAY FOR REAL-TIME MESOSCALE WEATHER INFORMATION