Handling the measurement error problem by means of panel data: Moment methods applied on firm data



1,...,n, and define the vector valued (G × 1) function of corresponding means taken
over all available observations,

(20)                 gn(y, x, z;β) = (1 /n) ∑nzj(yj - χjβ)

It may be considered the empirical counterpart to E[z0(y - )] based on the
sample. The
essence of GMM is to choose as an estimator for β the value which
brings the value of
gn (y, x, z; β) as close to its theoretical counterpart, the zero
vector 0
G,1, as possible. If G = K, an exact solution to the equation gn (y, x, z; β)=
0
G,1 exists and is the simple IV estimator

(21)                            β* = [P j z'jXj ] - 1[P j zjyi ]

If G>K, which is the most common situation, the GMM procedure solves the
estimation problem by
minimizing a distance measure represented by a quadratic
form in g
n(y, x, z; β) for a suitably chosen positive definit (G × G) weighting matrix
Wn, i.e.,

(22)   βGMM = βGMM(Wn) = argminβ[gn(y, x, z;β)0Wngn(y, χ, z;β)]

All estimators obtained in this way are consistent. The choice of Wn determines
the efficiency of the method. A choice which leads to an asymptotically efficient
estimator of
β, is to set this weighting matrix equal (or proportional) to the inverse
of (an estimate of) the (asymptotic) covariance matrix of (1
/n) Pjn=1 zj0j; see, e.g.,
Davidson and MacKinnon (1993, Theorem 17.3) and Harris and Matyas (1999,
section 1.3.3).

If is serially uncorrelated and homoskedastic, with variance σ2 , the appropriate
choice is simply
Wn = [n-2σ2 Pjn=1 zj0zj]-1. The resulting estimator obtained from
(22) is

(23)βbGMM =[(Pjx0jzj)(Pjz0jzj)-1(Pjz0jxj)]-1[(Pjx0jzj)(Pjz0jzj)-1(Pjz0jyj)],

which is the standard Two-Stage Least Squares (2SLS) estimator. The method can
also be fruitfully applied if
j has a heteroskedasticity of unspecified (or unknown)

11



More intriguing information

1. The name is absent
2. Fortschritte bei der Exportorientierung von Dienstleistungsunternehmen
3. The Role of State Trading Enterprises and Their Impact on Agricultural Development and Economic Growth in Developing Countries
4. Estimating the Technology of Cognitive and Noncognitive Skill Formation
5. The Clustering of Financial Services in London*
6. Growth and Technological Leadership in US Industries: A Spatial Econometric Analysis at the State Level, 1963-1997
7. The name is absent
8. Testing the Information Matrix Equality with Robust Estimators
9. The name is absent
10. The name is absent