Testing the Information Matrix Equality with Robust Estimators



To simplify the notations and calculations that follow we transform M in
order to diagonalise
V .Let

1+d 0 -d

W=  010,

-101

where

Eφ [(u4 - 6u2 + 3)(u2 - 1 - 2IF)] _ 1    1    ( 4

Eφ ((u4 - 6u2 + 3)2)       = 2 - 12 Eφ u

(8)


(9)


Then

1

WM = —
σ2

- 1 - d(μ4 - 6μ2 + 3)
ʌ        O .ʌ

μ3 - 3μ1

μ4 — 6 μ2 + 3


1 / u2 - 1 - 2IF (u; σ; Φ) - d (u4 - 6u2 + 3) ʌ

( Y ; θ ) = -2                  u3 - 3 u                  ,

σ               u4 - 6u2 +3

and V = WVW' is given by

1
V = σ4diag[A, 6, 24],

where

A = -8 + 4ASV(^) + 2E (u4IF) - 1 [E (u4IF)]2 .        (10)

We conclude that the IM test statistic in the normal model can be written
as the sum of three (asymptotically independent) statistics,

A+ (μ2 - 1 - d(μ4 - 6μ2 + 3))2 + 6(μ3 - 3μ1)2

(11)


+ 24(μ4 - 6μ2 + 3)2 .



More intriguing information

1. Life is an Adventure! An agent-based reconciliation of narrative and scientific worldviews
2. Survey of Literature on Covered and Uncovered Interest Parities
3. The name is absent
4. The name is absent
5. The name is absent
6. The name is absent
7. The name is absent
8. The name is absent
9. Mergers under endogenous minimum quality standard: a note
10. NATURAL RESOURCE SUPPLY CONSTRAINTS AND REGIONAL ECONOMIC ANALYSIS: A COMPUTABLE GENERAL EQUILIBRIUM APPROACH