Index
ISBN: 978-1-80262-066-5, eISBN: 978-1-80262-065-8
ISSN: 0731-9053
Publication date: 18 January 2022
This content is currently only available as a PDF
Citation
(2022), "Index", Chudik, A., Hsiao, C. and Timmermann, A. (Ed.) Essays in Honor of M. Hashem Pesaran: Panel Modeling, Micro Applications, and Econometric Methodology (Advances in Econometrics, Vol. 43B), Emerald Publishing Limited, Leeds, pp. 357-365. https://doi.org/10.1108/S0731-90532021000043B019
Publisher
:Emerald Publishing Limited
Copyright © 2022 Alexander Chudik, Cheng Hsiao and Allan Timmermann
INDEX
Index
Note: Page numbers followed by “n” indicate notes.
Active job market program
, 230
Activity limiting condition binary variable (ALC)
, 67
Adverse credit-supply shock
, 208
Aggregation methods
, 85–91
Alternative gradient methods
, 277
Amazon
, 87
Anderson and Rubin statistic (AR statistic)
, 341
“Anti-gang” campaign
, 97–98
Apple
, 87
Arellano–Bond difference GMM
, 308
ARX(1) model
, 104
Asymptotic distribution
, 287
of ML estimators
, 279–280
Asymptotic theory
, 108
mean non-stationarity
, 112–113
stationary setup
, 108–111
stylized autoregressive model
, 113–114
Augmented regression
, 107
Augmented Solow growth model
, 5, 298–300
Australian Household, Income and Labor Dynamic (HILDA)
, 67
Auto-regressive distributed lag approach (ARDL approach)
, 215–218
cross-sectionally augmented
, 219–220
Average treatment effects (ATE)
, 82
Backward mean transformation
approaches based on backward means
, 114
asymptotic theory
, 108–114
bias-corrected OBM
, 114–116
explanatory notes on Everaert
, 119–120
finite sample results
, 120–123
hybrid OLS-IV estimators
, 118–119
model
, 105–108
Monte Carlo results for dynamic model
, 127–143
OLS-IV estimator of Everaert
, 116–118
properties of GMM estimators
, 104–105
Balance-sheet
, 210
Bayesian analysis for dynamic panel data models
, 309
Bayesian approach
, 5
Bhattacharya-Matusita-Hellinger measure
, 233
Bias-corrected FE estimators
, 114
Bias-corrected OBM estimator (BC-OBM)
, 114–116, 121
Bias-corrected estimator
, 346
Block resampling bootstrap (2S bootstrap)
, 318
computation
, 330
Blundell–Bond system GMM
, 308
CCE mean group estimator (CCEMG)
, 189, 330
CCE pooled estimator (CCEP)
, 327
dynamic homogeneous panel
, 329
Central limit theorem (CLT)
, 147
Centrality
, 231
Chamberlain-type FE model
, 325
Chebyshev’s inequality
, 169
China’s P2P market, analysis of
, 97–98
Cluster-robust standard errors
, 146
Coherence
, 85
Common correlated effects (CCE)
, 38, 44–48, 84, 179, 308
Composition effects
, 230
Conditional maximum likelihood method
, 73
Conditional point estimation of endogeneity covariances
, 346
Confidence set
, 338, 345–352
ε-contamination
, 310, 312–313
Conventional measures of differences
, 238–340
Conventional simple average method
, 86
Conventional test statistic
, 149–155
Corporate debt
, 209
corporate debt–productivity growth
, 220
Corporate finance
, 208
Corporate indebtedness
, 209
Corporate-debt threshold effects, tests of
, 222–223
Correlation
coefficients
, 304
measures
, 281–282
Counterfactual analysis
, 237
Counterfactual distribution
, 238–244
accounting for selection
, 236–237
identification and estimation of
, 235
without selection
, 235–236
Coverage
, 211–213
CPDA approach
, 92
CPI
, 50
Crime, police effect on
, 197–200
Cross-correlation weights matrix
, 55
Cross-firm
heterogeneity
, 207
slope heterogeneity
, 208
Cross-section dependence test (CD test)
, 48, 50, 222
Cross-sectional correlation
, 146–147
conventional test statistic
, 149–155
modified test statistic
, 155–156
Monte Carlo experiment
, 156–165
review on double-indexed CLT
, 147–149
technical proofs
, 168–175
test
, 149
testing for cross-sectional correlation
, 149
Cross-sectional dependence (CD)
, 207
Cross-sectional error dependencies
, 209
Cross-sectionally augmented ARDL and DL approaches
, 219–220
Cross-Sectionally augmented Auto-Regressive Distributed Lag (CS-ARDL)
, 207
Cross-Sectionally augmented Distributed Lag (CSDL)
, 207
Cumulative distribution function (cdf)
, 272
replacing margins with empirical
, 280–281
Current Population Survey (CPS)
, 231, 237
Data generating process (DGP)
, 84, 151, 156, 192, 289
Debt
, 208
to assets
, 211
to EBITDA
, 211
of firm
, 210
overhang problem
, 208
threshold effect
, 209
Decision makers
, 82
Decree Law
, 210–211
Depth-based approach
, 185
Descriptive statistics
, 211
coverage
, 211–213
evolution of firm indebtedness
, 213
firm productivity
, 213–214
DHZ model
, 65
Diagonal OBM estimator (D-OBM)
, 121
Diebold–Mariano test
, 91
“Direct” approach
, 225n8
Disaggregate approaches
, 89–91
Distributed lag approach (DL approach)
, 219
cross-sectionally augmented
, 219–220
Double-indexed CLT
, 147
Dynamic binary state-dependent model
, 79–80
Dynamic heterogeneous panel data methods
, 4
Dynamic homogeneous panel data
dynamic heterogeneous panel data
, 329–
with CCE
, 329
with common trends
, 327–329
Dynamic panel data models
, 104, 114, 308, 310
Monte Carlo simulation study
, 319–330
random effects
, 308–309
robust linear dynamic panel data model
, 310–319
Dynamic qualitative choice models
, 79
Dynamic random coefficients panel data model
, 313
Dynamic response path of labor participation decision to health shock
, 65–70
Dynamic stochastic general equilibrium models (DSGEs)
, 64–65
Earnings distribution
, 230
Econometric models
, 10–11, 65, 272–275
Economic distance
, 146
Economic model
, 48–50
Economic significance
, 223–224
Eigenvector
, 86
Empirical model
, 49
Endogeneity
, 338–339
parameters
, 338
Endogeneity covariances
conditional point estimation of
, 346
inference for structural parameter
, 345–346
joint inference for structural parameters and
, 346–347
projection-based inference for
, 347–348
two-stage inference for
, 345
Entropy
, 238–340
entropy-based measures
, 233–234
Equity
, 49
Error components model
, 165n3
Error correction models (ECMs)
, 3, 38 (see also Panel data model)
spatial and spatio-temporal error correction models
, 39–44
Error-components
model
, 147
test
, 4
Estimation steps
, 61
Evaluation Functions (EFs)
, 233
Excessive debt
, 208
Exogeneity tests
, 350–351
Expectation hypothesis (EH)
, 256
LS with sequential thresholds, on original data
, 264–265
methodology
, 265–266
NP evidence
, 259–262
observations cause rejection of hypothesis
, 262
RLS on sorted data
, 262–264
Expectational errors
, 257–258
Expected squared error
, 258
Facebook
, 87
Female wage
, 238–244
Financial crisis
, 214
Financial institutions
, 1
Finite sample inference
, 293–296
Firm indebtedness
, 210
evolution
, 213
Firm(s)
, 208
firm-level panel data
, 4, 210
firm-specific lag order selection procedures
, 220
productivity
, 213–214
First-order dominance
, 234
Fixed effects (FE)
, 104, 108
dynamic panel estimator
, 308
estimators
, 104, 108, 178
model
, 73, 311
Forecasting accuracy
, 85
Frisch–Waugh–Lovell theorem (FWL theorem)
, 105, 342
g-prior
, 311
Gaussian dynamic linear mixed model
, 312–313
Gaussian pseudo-ML estimators
, 284
Gaussian ranks
, 270–271
asymptotic properties under correct specification
, 278
augmented Solow growth model
, 298–300
comparison
, 289
comparison with alternative estimators
, 287
correlations
, 272
econometric model
, 272–275
efficiency comparison with other moment estimators
, 281–284
empirical applications
, 297
growth regressions
, 301
margins
, 278–280
migration and growth rates
, 297–298
misspecification analysis
, 284–287
Monte Carlo evidence
, 289–297
partial correlation and regression
, 277–278
Pearson Correlation
, 287–289
practical considerations
, 304–306
regressions
, 272, 300
score vector and Hessian matrix
, 275–277
Spearman correlation
, 287
theoretical background
, 272
Gaussian regression procedures
, 300
Gaussian static linear mixed model
, 310
Generalized Kolmogorov-Smirnov test
, 235
Generalized method of moments (GMM)
, 104, 308
Global financial crisis
, 206
Global financial cycle
, 209
Google
, 87
Hard-threshold trimming
, 182
Hausman and Taylor (HT)
, 310, 319, 325–327
Health shock
, 65–70
Hessian function
, 277
Heterogeneity
, 238–239
Heterogeneous dynamic panel threshold models
, 214
Heterogeneous panels
, 178
Heterogeneous slope coefficients
, 178
Heterogeneous treatment effects
, 84–85, 92
Heteroskedasticity and autocorrelation consistent (HAC)
, 264
High-order network-lag Durbin model
, 2, 10
Higher-order network links
, 10
High-skill occupations
, 237
Homogeneity
, 178
Homogeneous temporal equilibrium
, 38
Homogeneous treatment effects
, 84–85, 92
Homogenous groups
, 85
House prices in UK
, 48
data
, 50
economic model
, 48–50
Hybrid OLS-IV estimators
, 118–119
Hypothesis testing
, 1, 92
Identification-robust inference (IR inference)
, 341
application to return-to-schooling model
, 351–352
asymptotic assumptions
, 343–345
basic structural framework
, 339–341
confidence regions
, 353
endogeneity parameters
, 338
exogeneity tests
, 350–351
framework and notation
, 339
inference approaches
, 338–339
inference for total effect
, 348–350
notation
, 341–343
two-stage inference for endogeneity covariances
, 345–348
Idiosyncratic shock
, 54
Implied Cobb–Douglas coefficients
, 298
Income-statement information
, 210
Independently and identically distributed (iid)
, 108
Individual behavior, panel analysis of
cohort approach to estimate fixed individual-specific effects for dynamic binary state-dependent model
, 79–80
dynamic response path of labor participation decision to health shock
, 65–70
parameter heterogeneity of state-dependent model
, 70–77
unemployment
, 64
Individual-specific slope coefficients
, 179
Industry-level deflators
, 225n10
Inference approaches
, 338–339
Inference for total effect
, 348–350
Information matrix equality
, 278–279
Institutional frameworks
, 207
Instrumental variables (IV)
, 338
Interest rates
, 256
Interquartile Range (IQR)
, 121
Inverse probability weighting methods
, 230
Isserlis’s theorem
, 345
Italian firms
ARDL approach
, 215–218
cross-sectionally augmented ARDL and DL approaches
, 219–220
data
, 210–211
descriptive statistics
, 211–214
DL approach
, 219
economic significance
, 223–224
empirical framework
, 214
estimates of long-run effects
, 220–222
productivity growth of
, 207–210
results
, 220
tests of corporate-debt threshold effects
, 222–223
TFP growth
, 206–207, 209
Job Corps programs
, 230
Joint inference for structural parameters and endogeneity covariances
, 346–347
Joint limit
, 147
Joint trimming approach
, 185
Kolmogorov-Smirnov test statistics
, 235
Korea Labor Income Panel Study (KLIPS)
, 183–184
Kullback-Leibler-Theil measure
, 231
Labor and product market frictions
, 209
Labor participation decision, dynamic response path of
, 65–70
LASSO method
, 84
Least median of squares (LMS)
, 272
Least squares (LS)
, 259, 308
estimators
, 105, 178
method
, 84
regression
, 258
with sequential thresholds
, 262
Least trimmed squares (LTS)
, 272
“Leverage ratchet” mechanism
, 225n4
Likelihood
based methods
, 104
based procedures
, 308
function
, 12
Likelihood-ratio-test (LR test)
, 11, 13, 15, 72
Linear approach
, 270
Linear cross-section regression model
, 146
Linear model
, 338
Linear panel regression model
, 146
Linear time-series regression model
, 146
Linearized version of EH
, 256
Log-likelihood score
, 276
Long-run effects, estimates of
, 220–222
Low-skill occupations
, 237
Lucas Critique
, 65
Macroeconomics
, 270
shocks
, 2
Mahalanobis depth
, 185
Mahalanobis-depth-based trimming
, 193, 200
March CPS
, 237
Marginal likelihoods
, 311, 314
Marginal propensity to consume (MPC)
, 183
Marginal trimming approach
, 184
Margins
, 278–280
replacing margins with empirical cdf
, 280–281
Maximum likelihood (ML)
, 272
Mean group estimator (MG estimator)
, 48, 178
Mean non-stationarity
, 112–113
Mean of absolute bias
, 88
Mean square error (MSE)
, 192
Medium-skill occupations
, 237
Micro modeling
, 4–5
Missing instruments
, 341
Misspecification analysis
, 284
asymptotic distribution
, 287
pseudo-true values
, 284–286
Model selection criterion
, 84
Modified test statistic
, 155–156
Monte Carlo evidence
, 289
design and estimation details
, 289
finite sample inference
, 293–296
effect of outliers
, 296–297
sampling distribution of different estimators
, 289–293
Monte Carlo experiment
, 156–165
Monte Carlo simulation
, 2–3, 5, 11, 13, 92–97, 147, 192–196
bias of parameters
, 16–23
Chamberlain-type FE model
, 325
design
, 13–14
DGP of Monte Carlo simulation study
, 319–321
dynamic homogeneous panel data model with CCE
, 329–330
dynamic homogeneous panel data model with common trends
, 327–329
individual-specific effects
, 14–15
likelihood-ratio tests
, 15
LR tests
, 32–34
results
, 15
RMSE of parameters
, 24–31
study
, 319
Multiple treatment effects
aggregation methods
, 85–87
analysis of China’s P2P market
, 97–98
criterion
, 87–89
homogeneous or heterogeneous treatment effects
, 84–85
measurement of treatment effects and sample configuration
, 82–84
Monte Carlo simulation
, 92–97
test of significance between aggregate and disaggregate approaches
, 89–91
treatment effects estimation results for impact of P2P performance
, 99
Multiplex network
, 10
Multivariate quantile contours
, 185
Nadaraya-Watson regression
, 258
Network interdependence
, 10
Network lag parameter
, 10
Newey-West estimators
, 262
Nickel bias
, 122
Nonparametric approach
, 83
Nonparametric estimation (NP estimation)
, 256
Normalized Bhattacharay-Matusita-Hellinger entropy
, 231
Normalized Kullback-Leibler-Theil measure
, 233
Null hypothesis
, 91
OBM implementation of Everaert (E-OBM)
, 121
OECD STAN database
, 211
Oil price shocks
, 209
OLS
coefficient
, 270
OLS-IV estimator of Everaert
, 116–118
regression
, 298
ORBIS data set
, 210
Orthogonal to Backwards Means estimator (OBM estimator)
, 3–4, 106
Outliers
, 256
effect of
, 296–297
Panel data model
, 2–4, 82–83, 104 (see also Dynamic panel data model; Error correction models (ECMs))
key assumptions
, 13
model
, 11
Monte Carlo simulations
, 13–34
random-effects
, 10–11
regression
, 178
Panel GMM estimators
, 309
Panel poolability tests
, 180
Panel regression model
, 189
Panel tests of threshold effects
, 218
Parametric approach
, 83
Partial correlation
coefficients and regression
, 277–278, 282–284
Pearson correlation coefficient
, 270–272, 287–289
Peer-to-peer activities (P2P activities)
, 82
Perpetual inventory method
, 211
Peso-problem explanation
, 256–259
Peso-type episodes
, 256
Police effect on crime
, 197–200
Policy invariant
, 64
Pooled mean group estimator
, 48
Pooled regression model
, 113
Posterior sensitivity analysis
, 313
Prais–Winsten transformation
, 309
Predetermined regressors
, 104–105
Productivity growth in Italy
, 206
Profit incentive
, 97
Projection-based inference for endogeneity covariances
, 347–348
Pseudo-true values
, 284–286
Purchasing Power Parity (PPP)
, 182–183
Quasi-maximum likelihood method (QML)
, 308
Quasi-Newton numerical optimization routine
, 276
Random effects (RE)
, 10, 73, 311, 308–309, 322–325
Ratio of debt
, 210
Real business cycle models
, 64
Real capital stocks
, 211
Recursive estimation
, 266
Recursive LS (RLS)
, 262
on sorted data
, 262–264
Recursive Mean Adjustment estimator (RMA estimator)
, 113
Rejection frequencies (RF)
, 121
Reporting assets
, 210
Return-to-schooling model, application to
, 351–352
Robust dynamic linear model in two-stage hierarchy
, 314–318
Robust estimator
, 181
Robust linear dynamic panel data model
, 310
dynamic framework
, 312–314
estimating ML-II posterior variance–covariance matrix
, 318–319
robust dynamic linear model in two-stage hierarchy
, 314–318
static framework
, 310–312
Robustness
, 182
testing
, 231
Root-mean-squared-error (RMSE)
, 11, 88
Sampling distribution of different estimators
, 289–293
Second-order dominance
, 234
Semi-parametric method
, 84
Short-term economic policies
, 64
Short-term reversal strategies
, 270
Sign test
, 91
Simple bootstrap technique
, 235
Simultaneous equation models
, 65, 340
Single equation approach
, 66
Single-equation instrumental variable approach
, 211
Slope homogeneity tests
, 180
Small and medium enterprises (SMEs)
, 97
Smoothed Fama-Bliss estimation method
, 259
Solow growth model
, 272
Spatial error correction
, 44
Spatial interdependence
, 10
Spatial parameter
, 10
Spatial temporal error correction models
, 39–44
Spatial weights matrix
, 41, 47, 54, 146, 151
Spatio-temporal error correction models
, 38–48
Spatio-temporal framework
, 38
Spearman correlation
, 287, 302n2
State-dependent model
, 66
parameter heterogeneity of
, 70–77
Static framework
, 310
Stationary setup
, 108–111
Stochastic dominance (SD)
, 231, 234–235
results
, 240
tests
, 233–235
Structural effects
, 230
Structural vector autoregressive process
, 121
Stylized autoregressive model
, 113–114
Symmetrized Kullback-Leibler-Theil measure
, 233
Tax deductibility of interest payments
, 208
Temporal equilibrium
, 42
Temporal error correction
, 38, 44
Term structure of interest rates
, 256
Three-stage hierarchy framework
, 310
Threshold effects, estimation and panel tests of
, 218
Time-series regression model
, 146
Total factor productivity growth (TFP growth)
, 206–207
Traditional dynamic dependence model
, 65
Traditional macroeconometric models
, 64
Treatment effect
, 82
Trimmed CCE mean-group estimator (TCCEMG estimator)
, 189–191
Trimmed mean group estimation
, 185
examples
, 182–184
MG estimator
, 178
Monte Carlo simulation
, 192–196
motivation
, 179
police effect on crime
, 197–200
trimmed CCEMG estimator
, 189–191
trimmed MG estimator for two-way FE models
, 185–188
trimming based on variances of regressors
, 180–182
trimming weights
, 184–185
weighted mean group estimation
, 179–180
Trimmed mean group estimator (TMG estimator)
, 181
Trimming
methods
, 4
weights
, 184–185
Two-digit gross fixed capital formation
, 211
Two-stage approach
, 225n8
Two-stage hierarchy
first step of robust Bayesian estimator
, 314–317
robust dynamic linear model in
, 314
second step of robust Bayesian estimator
, 317–318
Two-step approach
, 211
Two-stage inference for endogeneity covariances
, 345–348
Two-way FE regression
, 197
Type-II ML (ML-II)
, 310, 317
estimating ML-II posterior variance–covariance matrix
, 318–319
Unconditional likelihood function
, 308
Uncorrelatedness assumption
, 146
Unemployment
, 64
Variance–covariance matrix
, 316
estimating ML-II posterior
, 318–319
Wage distributions
, 231
Wald test statistics
, 72
Weak dependence
, 44–48
Welfare functions
, 233–234
Wick’s theorem
, 345
Wilcoxon’s signed-rank test
, 91
Women’s potential earnings distributions
baseline results
, 238
basic notations
, 232–233
comparing two distributions
, 233–235
data
, 237–238
earnings
, 230–231
empirical methods
, 232
female wage vs. counterfactual distribution
, 238–244
identification and estimation of counterfactual distributions
, 235–237
results addressing selection
, 244–248
stochastic dominance results with selection correction
, 249
women’s human capital characteristics
, 231–232
Zellner g-prior
, 313
Zero-coupon Treasury bonds
, 259
- Prelims
- Introduction
- Part B1: Panel Data Methods
- Chapter 1: A Panel Data Model with Generalized Higher-Order Network Effects
- Chapter 2: Spatial and Spatio-Temporal Error Correction, Networks and Common Correlated Effects
- Chapter 3: Heterogeneity and Dynamic Dependence in Panel Analysis of Individual Behavior
- Chapter 4: Multiple Treatment Effects in Panel-Heterogeneity and Aggregation
- Chapter 5: Backward Mean Transformation in Panel Data with Predetermined Regressors
- Chapter 6: Various Asymptotic Distributions of the Error-Components Test for Cross-Sectional Correlation
- Chapter 7: Trimmed Mean Group Estimation
- Part B2: Micro Modeling
- Chapter 8: Corporate Indebtedness and Low Productivity Growth of Italian Firms
- Chapter 9: Women’s Potential Earnings Distributions
- Part B3: Econometric Methodologies
- Chapter 10: Where (and by How Much) Does a Theory Break Down? With an Application to the Expectation Hypothesis
- Chapter 11: Gaussian Rank Correlation and Regression
- Chapter 12: Robust Dynamic Panel Data Models Using ε-Contamination
- Chapter 13: Identification-robust Inference for Endogeneity Parameters in Models with an Incomplete Reduced Form
- Index