Testing the Information Matrix Equality with Robust Estimators



Hence


b = lim nEEFs [ s ( Y ; β0 ,n 0 ,n, 0)]
n→∞

0

=e 0

\ 1 -∏
\ 2 π


The information matrix is

J = E [s (y ;0, 1, 0) s (y ;0, 1, 0)' ]

1  0  Eφ[u(u2 1)I(u > 0)] \

 2  Eφ[(u2 1)21(u> 0)]

■   ■  Eφ[(u2 1)21(u> 0)] J

10φ(0) \

021 ,

φ(0)  1    1

wherefrom δ = b,J 1 b = π-1 e2.

2π


C.3 Tilted normal alternative


Expanding f(y; β, σ, κ, λ) around κ =0andλ = 0 gives


f( У ;β,σ,κ,λ ) = 1 φ ( u )
σ


κλ

1 + ^( u — 3 u ) + 24( u — 6 u + 3)


+ o(κ, λ),


from which the moments given in (15) follow. The score function, evaluated
at
κ = λ =0, is


s(y; β, σ, 0, 0)


σ u \

u2 -1
σ
u3 3 u
6
u4 6u 2+3
\     24     /


The information matrix is


J = E [s ( y ; β, 1, 0, 0) s ( y ; β, 1, 0, 0) ']

/ 1 0 0   0 \

0200

=     0 0 1  0    

V 0 0 0 24 J


35




More intriguing information

1. Secondary stress in Brazilian Portuguese: the interplay between production and perception studies
2. Business Networks and Performance: A Spatial Approach
3. Endogenous Determination of FDI Growth and Economic Growth:The OECD Case
4. The name is absent
5. THE USE OF EXTRANEOUS INFORMATION IN THE DEVELOPMENT OF A POLICY SIMULATION MODEL
6. The name is absent
7. GENE EXPRESSION AND ITS DISCONTENTS Developmental disorders as dysfunctions of epigenetic cognition
8. The name is absent
9. Word Sense Disambiguation by Web Mining for Word Co-occurrence Probabilities
10. The name is absent