Testing Panel Data Regression Models with Spatial Error Correlation



Using (A.2), one obtains

∂L
∂σ
2

I Hd =

2tr[ u 1(It   (B0B)-1)]+ 2[U0 U1 (It   (B,B)~1) U1 u]

=

v tr[( v2 Jt + v2 Eτ ) In ] + v[u0[( V4 Jτ + v4 Eτ ) In ]u]      (A.12)

2    ^1      ¾°              2     ¾ 1      ¾ °

∂L
μ

=

N(T — 1)     N  ,  1 „0, 1 -     1 ʌʌ ,  1 ʌ,, 1         .        n

vv2     vv2 + uu ( V4 jt  in)u + vu (~et  in)u = 0,

2¾°      2¾1   2   ¾1              2   ¾ °

jH0d  =

2tr[ U 1(jt   in)] + 2[u0 U 1(jt   in) U 1u]                     (A.13)

nt    1 r„,z^           „

=

TTT + TΓ4 [u(JT  1N)u] = 0;

2¾ 1    2¾ 1

∂L

Ж

jHod  =

2tr[ U 1(¾2It   (W + W0))] + ∣[u0 U 1(¾2It   (W + W0)) U 1u]

=

-12 [u0(Eτ  (W + W 0))u] + ⅛ [u0(J0τ  (W + W 0))^] = D λ,    (A.14)

2¾°                          2¾1

where ¾° = ^0(Eτ In)u∕N(T — 1) and ¾2 = ^0(Jτ  In)u∕N are the maximum likelihood

estimates of ¾° and σ2, and u is the maximum likelihood residual under the null hypothesis
Hd
H0 .

Therefore, the score vector under Hd is given by

0

0

(A.15)


ʌ

D λ

Using (A.5), the elements of the information matrix are given by

J11 = e [ g(¾L)2 ] =2 tr[(((σι2jr + σJ2Eτ )   in ))]                     (A.16)

_ N l 1 T 1 ʌ

= у M + ~°^~ ɔ;

J22 = E [ — @@22 ] =2 tr[(((¾Γ2 Jτ + ¾-2 Eτ )   In )( Jt In ))2]          (A.17)

~∖~μ∕

_ NT2

= l¾f ’

j33 = E [ @\2 ] =2tr[(((σ1 2 jT + σ!72ET)   in)

= ¾4 tr ' ( ¾1 1J/ + ¾-4Eτ )   (2W2 + 2W 0W


(¾°It   (W + W0)))2] (A.18)

: ( ¾° + (T 1))b,

4¾1            /

22



More intriguing information

1. Towards Teaching a Robot to Count Objects
2. The name is absent
3. The name is absent
4. The name is absent
5. The name is absent
6. Institutions, Social Norms, and Bargaining Power: An Analysis of Individual Leisure Time in Couple Households
7. A Bayesian approach to analyze regional elasticities
8. The name is absent
9. The storage and use of newborn babies’ blood spot cards: a public consultation
10. Evaluation of the Development Potential of Russian Cities