Large-N and Large-T Properties of Panel Data Estimators and the Hausman Test



Lemma 2 Under Assumptions 1-8, we obtain the following results as (N, T
). For some positive semidefinite matrices Ψx and Ξ (defined in the Ap-
pendix),

(a) NN ΣiT ∑t Gχ,τXitXitGχ,τ p Ψχ;

(b)1N Pi T Pt Gx,Txitvit N (0, σvψx) ;

(c) 11 Pi DTwiweDT p ξ;

(d) √⅛∑i DTWivi p 0(k+g)×ι.

Lemma 3 Under Assumptions 1-8 and Assumption 11 (local alternatives to
random e
ffects), as (N, T →∞),

N Pi Dt wu N (λ σU≡0.

Lemma 4 Under Assumptions 1-8 and Assumption 10 (fixed effects),

N Pi Dτ wiei pΞλ,

as (N,T →∞) .

The following assumption is required for identification of the within and
between estimators of
β and γ.

Assumption 12 The matrices Ψx and Ξ are positive definite.

Two remarks on this assumption follow. First, this assumption is also sufficient
for identification of the GLS estimation. Second, while the positive definiteness
of the matrix Ξ is required for identification of the between estimators, it is not
a necessary condition for the asymptotic distribution of the Hausman statistic
obtained below. We can obtain the same asymptotic results for the Hausman
test even if we alternatively assume that within estimation can identify
β (pos-
itive definite Ψ
x) and between estimation can identify γ given β (the part of
Ξ corresponding to
zei is positive definite).18 Nonetheless, we assume that Ξ is
invertible for convenience.

We now consider the asymptotic distributions of the within, between and
GLS estimators of
β and γ:

we can show that

E(ui | Xi, Zi) = Xiλχ + Ziλz,
where d = (σf + σ2∕T)(σf + ση) — σf, λχ = — f ση/d, λz = c(σf + σ2∕T)ση/d. Observe
that
λx 6=0, if λz 6=0(c 6= 0). Thus, λx is functionally related to λz . In addition, it is easy
to show that
plimN→∞βb = β + λx 6= β, if λz 6=0(c 6= 0). Thus, nonzero λz biases βb.

18 This claim can be checked with the following simple example. Consider a simple model
with one time-varying regressor
xit and one time invariant regressor zi . Assume that xit =
azi + eit , where the eit are i.i.d. over different i and t. For this model, it is straightforward
to show that the matrix Ξ fails to be invertible. Nonetheless, under the random effects
assumption, the Hausman statistic can be shown to follow a
χ2 distribution with the degree
of freedom equal to one.

26



More intriguing information

1. Philosophical Perspectives on Trustworthiness and Open-mindedness as Professional Virtues for the Practice of Nursing: Implications for he Moral Education of Nurses
2. Inhimillinen pääoma ja palkat Suomessa: Paluu perusmalliin
3. Analyzing the Agricultural Trade Impacts of the Canada-Chile Free Trade Agreement
4. Evaluating the Impact of Health Programmes
5. CREDIT SCORING, LOAN PRICING, AND FARM BUSINESS PERFORMANCE
6. The name is absent
7. The Integration Order of Vector Autoregressive Processes
8. The name is absent
9. The name is absent
10. Improvements in medical care and technology and reductions in traffic-related fatalities in Great Britain