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



Since SZeeZ and SZωZ coincide asymptotically, we get, using bars to denote plims,

(A.4)


V( √N β ) = [ S XZ


ZZSZX]-1[S


XZ


ZZ


ZΩZ SZZ sZX ][SXZ szz sZX ] 1,


(A.5)


V( 4N β ) = [ S XZ


- Ω Z SZX] 1


Replacing the plims Sxz, Szx, SZZ and SZωz by their sample counterparts,

Sxz, SZX, SZZ and SZêêZ and dividing by N, we get from (A.4) and (A.5) the
following estimators of the asymptotic covariance matrices of
βb and βe :
(A.6)
V(β) = N [SXZS-ZSZX] 1[SXZSZZSZ..Zs-ZsZX][sXZs-ZsZX] 1

= [X0PZX]-1[X0PZbb0PZX][X0PZX]-1,

(A.7) Vdd ) = N S XZ S -. . - S ZX ]1

= [ X 0Z ( Z 0bb. 0Z )-1Z 0X ]-1 = [ X 0P Z (b b0 ) X ]-1

These are the generic expressions which we use for estimating variances and co-
variances of the GMM estimators considered.

When calculating β from (A.3) in practice, we replace PZ(Ω) by PZ(bê0) =

Z(Z0 .b.b0Z)-1Z0 [see White (1982, 1984)].

30



More intriguing information

1. The name is absent
2. Shifting Identities and Blurring Boundaries: The Emergence of Third Space Professionals in UK Higher Education
3. Parallel and overlapping Human Immunodeficiency Virus, Hepatitis B and C virus Infections among pregnant women in the Federal Capital Territory, Abuja, Nigeria
4. Declining Discount Rates: Evidence from the UK
5. The name is absent
6. The name is absent
7. The name is absent
8. Foreign Direct Investment and Unequal Regional Economic Growth in China
9. The name is absent
10. Are Public Investment Efficient in Creating Capital Stocks in Developing Countries?