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



Lastly, the following theorem finds the asymptotic distribution of the Haus-
man test statistic under the random effect assumption and the local alternatives:

Theorem 9 Suppose that Assumptions 1-8 and 12 hold. Corresponding to the
size ofi,z0)0, partition Ξ and λ, respectively, as follows:

Ξxx Ξxz            λx

Ξ =   Ξ0xz Ξzz   ; λ =   λz   .

Then, as (N,T →∞),

(a) under Assumption 9 (random effects),

HMNT χ2k ;

(b) under Assumption 11 (local alternatives to random effects),

HMNT χ2k (η),

where η = λ0x xx ΞxzΞ-1Ξ0xz)λx2l is the noncentral parameter.

Theorem 9 shows that under the random effects assumption, the Hausman
statistic is asymptotically χ
2-distributed with degrees of freedom equal to k
(the number of the time-varying regressors). Furthermore, Theorem 9 (ii) shows
that the Hausman statistic has significant local power to detect any correlation
between the time-varying regressors x
it and the effect ui . This is so, because
the noncentral parameter η equals zero if, and only if, λ
x = 0k×1 . In contrast,
the noncentrality parameter η does not depend on λ
z , indicating that the Haus-
man test has no power to detect nonzero correlations between time invariant
regressors z
i and the individual effect ui in the direction of our local alternative
hypotheses (Assumption 11). This result holds even if T is finite and fixed. As
discussed earlier, this is due to the fact that the conditional mean of the effect u
i
is a linear function of regressors under our local alternative hypotheses. When
the conditional mean is not linear, the Hausman test could have a power to
detect nonzero correlations of the effect u
i with the time invariant regressors.
However, the power of the Hausman test to such correlations is generally lim-
ited. This is so because the Hausman test can detect such correlations only if
they can cause a large bias in the between estimator of β, the coefficient vector
on time-varying regressors (see Ahn and Low, 1996).

5 Conclusion

This paper has considered the asymptotic properties of the popular panel data
estimators and the Hausman test. We find that the convergence rates of the
estimators and the test statistic are sensitive to data generating process. In
particular, the convergence rates of the between estimator crucially depend on
whether the data are cross-sectionally heteroskedastic or homoskedastic. De-
spite the different convergence rates, however, the estimators are consistent and

29



More intriguing information

1. The Provisions on Geographical Indications in the TRIPS Agreement
2. BODY LANGUAGE IS OF PARTICULAR IMPORTANCE IN LARGE GROUPS
3. Integration, Regional Specialization and Growth Differentials in EU Acceding Countries: Evidence from Hungary
4. RETAIL SALES: DO THEY MEAN REDUCED EXPENDITURES? GERMAN GROCERY EVIDENCE
5. The demand for urban transport: An application of discrete choice model for Cadiz
6. Three Strikes and You.re Out: Reply to Cooper and Willis
7. Co-ordinating European sectoral policies against the background of European Spatial Development
8. I nnovative Surgical Technique in the Management of Vallecular Cyst
9. A Brief Introduction to the Guidance Theory of Representation
10. Synthesis and biological activity of α-galactosyl ceramide KRN7000 and galactosyl (α1→2) galactosyl ceramide
11. The name is absent
12. Educational Inequalities Among School Leavers in Ireland 1979-1994
13. CONSUMER PERCEPTION ON ALTERNATIVE POULTRY
14. THE CHANGING STRUCTURE OF AGRICULTURE
15. Changing spatial planning systems and the role of the regional government level; Comparing the Netherlands, Flanders and England
16. The name is absent
17. Correlation Analysis of Financial Contagion: What One Should Know Before Running a Test
18. Models of Cognition: Neurological possibility does not indicate neurological plausibility.
19. An Economic Analysis of Fresh Fruit and Vegetable Consumption: Implications for Overweight and Obesity among Higher- and Lower-Income Consumers
20. Rural-Urban Economic Disparities among China’s Elderly