A Principal Components Approach to Cross-Section Dependence in Panels



Table 1A. Monte Carlo simulation results

N =30,T

= 300, γi

= 1, ρdi

=0, ρz

=0, σ2di

=1

A) Regression I

Mean

SSD

Min.

Max.

Skew.

Kurt-3

MG estimator

ʌ
^

1.4983

.0217

1.4243

1.5584

.0544

.0215

ʌ

SEι(θ)

.0083

.0011

.0056

.0116

.1819

-.2505

FE estimator

ʌ
^

1.4975

.0216

1.4244

1.5579

.0593

.0299

ʌ

SEι(θ)

.0092

.0002

.0087

.0096

-.1818

.0738

ʌ

SE2(θ)

.0169

.0003

.0161

.0179

.2264

.2835

ʌ

SE3(θ)

.0222

.0014

.0189

.0291

.7026

1.3561

POLS estimator

ʌ
^

1.4967

.0216

1.4232

1.5573

.0589

.0382

ʌ

SE1(θ)

.0092

.0002

.0087

.0096

-.1829

.0829

ʌ

SE2(b)

.0169

.0003

.0161

.0179

.2299

.3072

ʌ

SE3(θ)

.0221

.0015

.0180

.0277

.5705

.6412

B) Regression II

Mean

SSD

Min.

Max.

Skew.

Kurt-3

MG_______________________________

ʌ
b

1.0987

.0165

1.0503

1.1464

.2764

-.1859

ʌ

SE1(b)

.0100

.0013

.0063

.0137

.1158

-.0758

FE_________________________________________

ʌ
b

1.0980

.0163

1.0517

1.1459

.2769

-.1551

ʌ

SE1(b)

.0097

.0001

.0094

.0101

.0156

-.0846

ʌ

SE2(b)

.0098

.0001

.0095

.0103

.2678

.1741

ʌ

SE3(b)

.0109

.0006

.0092

.0133

.2375

.3445

POLS_______________________________________

ʌ
b

1.0977

.0163

1.0506

1.1453

.2678

-.1418

ʌ

SEi(b)

.0097

.0001

.0094

.0100

.0219

-.1046

ʌ

SE2(b)

.0098

.0001

.0095

.0103

.2678

.1635

ʌ

SE3(b)

.0109

.0006

.0093

.0131

.2703

.2165

Note: SE1 is based on the usual covariance matrix formulae for the MG, FE and
POLS estimators.
SE2 is based on (10) and SE3 is based on (13).

21



More intriguing information

1. The use of formal education in Denmark 1980-1992
2. The name is absent
3. Nonparametric cointegration analysis
4. The name is absent
5. Convergence in TFP among Italian Regions - Panel Unit Roots with Heterogeneity and Cross Sectional Dependence
6. Endogenous Heterogeneity in Strategic Models: Symmetry-breaking via Strategic Substitutes and Nonconcavities
7. The Nobel Memorial Prize for Robert F. Engle
8. The name is absent
9. LABOR POLICY AND THE OVER-ALL ECONOMY
10. Perfect Regular Equilibrium