Testing the Information Matrix Equality with Robust Estimators



where q is the rank of V . Remark that T can also be written as

τ = n W^My Wvwɔ + WW ,

where W is any non-singular q × q matrix. Choosing W so as to make
WVW' diagonal simplifies T, and this will be exploited below.

Note that if, say, the j-th column of D(θ) is zero, then V is independent
of the estimator
θj (the j-th element of θ) that is used. When V has full
rank, an obvious estimator is

-1


1n

- ∑ξ ( Xi,Yi ; θ) ξ ( Xi ,Yi ; θ) )

i=1

For the ML estimator we have

IF( X,Y ; Θml ; K,Fθ )


=—Ee ∂sθ(χ,γ) ) sθ(χ,γ)


It may occur that (some elements of) D(θ) need to be estimated by empirical
counterparts.

3 The normal model

3.1 The IM test

For the normal model without covariates, Fθ(y) = 1 Φ(y-β) with θ = (β, σ))
and Φ the standard normal cdf. Letting u = (Y — β), we have (White,
1994, p. 332-333)

1 / u 2 1

m ( Y ; θ ) = — I    u3 3 u

σ    u4 5u2 +2

            ι /    2 u         4 u2 2

—— m ( Y ; θ ) = 3 I 3 u2 3      5 u3 9 u

∂θ           σ    4u3 10u 6u4 20u2 +4

1  02

D ( θ ) =--3   0 0   ,

σ  02



More intriguing information

1. TOMOGRAPHIC IMAGE RECONSTRUCTION OF FAN-BEAM PROJECTIONS WITH EQUIDISTANT DETECTORS USING PARTIALLY CONNECTED NEURAL NETWORKS
2. Evidence on the Determinants of Foreign Direct Investment: The Case of Three European Regions
3. The name is absent
4. Private tutoring at transition points in the English education system: its nature, extent and purpose
5. Opciones de política económica en el Perú 2011-2015
6. A Pure Test for the Elasticity of Yield Spreads
7. Prizes and Patents: Using Market Signals to Provide Incentives for Innovations
8. Towards Teaching a Robot to Count Objects
9. Feature type effects in semantic memory: An event related potentials study
10. The Importance of Global Shocks for National Policymakers: Rising Challenges for Central Banks