Testing Panel Data Regression Models with Spatial Error Correlation



J12 = E h - @@@ ■'i = 2teh((¾Γ2JT + ¾-2Et)  InK2(Jt  In)]        (A.19)

- °-' Ц-     —

_ NT

= 2¾4,

J13 = Eh - 2i = 24((¾1^2JT + ¾-2ET)  In)

(A.20)


(A.21)


((¾-2Jr + --2Et )  In )(-° It  (W + W 0))i = 0,

@2L

J23 =


E [-@ 2 ∂λ J = 2 tr ¾12(JT  In )((¾ι2tJτ + ¾°ET )   In )

n

2

(¾° It  (W + W 0))i = tr h 14J Jt  (W + W 0)i = 0,

2    ¾1

where the result that J13 = J23 = 0 follows from the fact that the diagonal elements of W is
0 and
J33 uses the fact that tr(W2) = tr(W02), and b = tr(W 2 + W0W).

Therefore, the information matrix evaluated under H0d is given by

Γ Nl 1 i τ-1

2 (¾1 + ¾° )

NT

2<^1

0

ʌ

NT

NT 2

jμ =

2¾4

2<^1

0

0

0

4

(T - 1 + ¾4)b _

Therefore,

LMχ = D0x J- Dλ

= D(A)2

[(T - 1) + ¾4]b,


(A.22)


as described in (2.24).

Appendix A.3: Conditional LM test for ¾2 = 0 (assuming ʌ = 0)

This appendix derives the conditional LM tests for zero random regional effects assuming that
spatial error correlation exists. We give the detailed derivation of the score and information
matrix for testing
H0e : -2n = 0 (assuming A 6= 0).

Under H0e,

0  =  -° It   (B0B)-1,

(A.23)

(A.24)


-1  =  ^12 It   (B0B),

2

23



More intriguing information

1. How does an infant acquire the ability of joint attention?: A Constructive Approach
2. Nonlinear Production, Abatement, Pollution and Materials Balance Reconsidered
3. TRADE NEGOTIATIONS AND THE FUTURE OF AMERICAN AGRICULTURE
4. Research Design, as Independent of Methods
5. BARRIERS TO EFFICIENCY AND THE PRIVATIZATION OF TOWNSHIP-VILLAGE ENTERPRISES
6. Handling the measurement error problem by means of panel data: Moment methods applied on firm data
7. Wounds and reinscriptions: schools, sexualities and performative subjects
8. THE CO-EVOLUTION OF MATTER AND CONSCIOUSNESS1
9. The name is absent
10. A Classical Probabilistic Computer Model of Consciousness