Íàøëè îïå÷àòêó? Âûäåëèòå åå ìûøêîé è íàæìèòå Ctrl+Enter
Íàçâàíèå: Analysis of panel data
Àâòîð: Hsiao C.
Àííîòàöèÿ:
Review
"Cheng Hsiao has made many significant and important contributions to panel data econometrics, both methodological and applied, beginning with his 1972 dissertation, in numerous articles, and in his masterful and magisterial 1986 monograph, long a standard reference and popular graduate text. (cont.)
Not only has Hsiao significantly revised the material covered in his original monograph, he has added major new chapters on nonlinear panel models of discrete choice and sample selection, and included new material on the Bayesian treatment of models with fixed and random coefficients, pseudopanels, simulation methods of estimation, and more extensive treatment of dynamic models. Throughout, Hsiao provides applied examples, which greatly enhance the reader's understanding and intuition. The clarity of his exposition and organization is exemplary. All of us who work in the field of panel data econometrics have been, and will now more than ever continue to be in Hsiao's debt." Marc Nerlove, University of Maryland
"The literature on panel data modeling has seen unprecendented growth over the past decade and Cheng Hsiao, himself one of the leading contributors to this literature, is to be congratulated for providing us with a comprehensive and timely update of his classic text. This version not only presents a substantial revision of the 1986 edition, but also offers major additions covering non-linear panel data models dealing with useful overviews of unit root and cointegration in dynamic heterogeneous panels. It should prove invaluable to students and teachers of advanced undergraduate and graduate economic courses." Hashem Perasan, Trinity College, Cambridge
"The first edition of Analysis of Panel Data by Cheng Hsiao has been necessary reading and a landmark for 15 years. The revised and much expanded second edition splendidly integrates the important new developments in the field. One can be sure it will stay a landmark for 15 years to come." Jacques Mairesse, ENSAE, France
"Cheng Hsiao has done a great service to the profession by expanding his highly successful first edition to include the important results that have been obtained by him and other researchers since the publication of the first edition. Escpecially noteworthy in this edition is the application of panel data analysis to qualitative response and sample selection models. Cheng has admirably succeeded in presenting the mathematical results both rigorously and lucidly. Many theoretical results are illustrated by interesting empirical examples. This edition should prove to be an extremely useful reference for the experts in the field as well as graduate students." Takeshi Amemiya, Stanford University
Book Description
Panel data models have become increasingly popular among applied researchers due to their heightened capacity for capturing the complexity of human behavior, as compared to cross-sectional or time series data models. This second edition represents a substantial revision of the highly successful first edition (1986). Recent advances in panel data research are presented in an accessible manner and are carefully integrated with the older material. The thorough discussion of theory and the judicious use of empirical examples make this book useful to graduate students and advanced researchers in economics, business, sociology and political science.
Acceleration sales model22 Adaptations in behavior268—269 Advantages of panel data competing hypotheses312—313 Advantages of panel data degrees of freedom and multicollinearity311—312 Advantages of panel data distributed-lag model estimation5 Advantages of panel data dynamics of change3—4 Advantages of panel data estimation bias reduction313—316 Advantages of panel data measurement errors5—6 Advantages of panel data micro foundations for aggregate data analysis316 Advantages of panel data two-dimensional nature of data7—8 Aitken estimator123150155165320 Analysis of covariance14—26 Analysis of covariance descriptive model14—15 Analysis of covariance example from Kuh21—26 Analysis of covariance main steps in15 Analysis of covariance one-way150 Analysis of covariance problems in tracing heterogeneity20—21 Analysis of covariance regression over individuals15—182330—33 Analysis of covariance regression over time18—2024—25 Analysis of covariance summary of tests for homogeneity19 Analysis of variance14 Argument Dickey — Fuller (ADF) t-ratios301 Attrition probability234—238 Autoregressive models in short panelsvector autoregressive models268275 Autoregressive moving-average (ARMA)157 Bandwidth parameter231249 Bayes estimators146170177—180 Bayes solutions168—170174—175 Bayes updating formula175 Bernoulli models207 Best linear unbiased estimator (BLUE) in variable-coefficient models154—155164 Best linear unbiased estimator (BLUE) in variable-intercept models313335455355 Best linear unbiased predictor (BLUP)170 Between-group estimators37 Bias attrition239 Bias Bayes estimator178—180 Bias covariance estimator72 Bias fixed-effects probit models198—199 Bias from dynamic structure315—316 Bias generalized least-squares estimator85 Bias generalized method of moments90101—102 Bias heterogeneous intercepts9—10 Bias income-schooling model113—114127 Bias IV estimator101—102 Bias maximum likelihood estimation91—93101—102211 Bias measurement errors5304—309316 Bias minimum-distance estimator101 —102 Bias OLS estimator73—74 Bias omitted-variable313—315 Bias selectivity9—11254 Bias simultaneity316 Box-Jenkins method163 Capital intensity183 Cash-flow effect26180—181 Categorical modelsdiscrete data cell-mean corrected regression models16—1723 Censored model, definitiontruncated and censored models225 Chamberlain approach60—65 Chamberlain minimum-distance estimator83 Clustering structure302—304 Cobb — Douglas production functions28—29 Cohorts283—285329 Cointegration rank323 Competing hypotheses312—313 COMPUSTAT data181 Conditional vs. marginal likelihood functionslikelihood functions43—49 Correlations, arbitrary103—104 Covariance (CV) estimator dynamic panel data models71—72 Covariance (CV) estimator random-vs. fixed-effects models69—70 Covariance (CV) estimator simple regression with variable intercept models355355 Covariance transformation, measurement error and305—306 Cramer — Rao bounds50 Cross-sectional data consisting of entire population329 Cross-sectional data difficulties of describing dynamics of change from4 Cross-sectional data pooled with time-series data285—290329 Cross-sectional data repeated283—285 Cross-sectional dependence309—310 Cumulative normal distribution190 Degrees of freedom311—312 Depreciation rate95 Diagonal-path limits approach296 Discrete datadynamic discrete data models definition188 Discrete data dependent variable assuming only two values188—189 Discrete data discrete-response models188—193 Discrete data dynamic models206—224 Discrete data existence of a consistent estimator.195—198 Discrete data female employment example193218—222 Discrete data fixed-effects models194—199 Discrete data household brand choices example221—224 Discrete data maximum likelihood estimator194—195 Discrete data Monte Carlo evidence198—199 Discrete data parametric approach to static models with heterogeneity193—202 Discrete data random-effects models199—202 Discrete data semiparametric approach to static models202—206 Discrete data state dependence vs. heterogeneity216—218222 Discrete data unemployment theory216 Distributed lag estimation in short panels268—279 Distributed lag estimation in short panels common assumptions270—271 Distributed lag estimation in short panels, estimation and testing277—279 Distributed lag estimation in short panels, general distributed-lag model269270271 Distributed lag estimation in short panels, identification using lag coefficients275—277 Distributed lag estimation in short panels, identification using the exogenous variable271—275 Distributed lag estimation in short panels, progressive nature of adaptations268—269 Distributed lag estimation in short panels, rates of return example278—279 Distributed-lag models5269270271 Distributions, combination of normal185—187 Dummy variables, least-squaresleast-squares dummy-variables Dynamic censored Tobit models259—265 Dynamic discrete data models206—224 Dynamic discrete data models conditional probability approach211—216 Dynamic discrete data models general model106—108 Dynamic discrete data models, household brand choices example221—224 Dynamic discrete data models, initial conditions208—211 Dynamic discrete data models, state dependence vs. heterogeneity216—218222 Dynamic discrete data models, unemployment theory216 Dynamic models with variable interceptsfixed-effects models; random-effects models69—112 Dynamic models with variable intercepts, arbitrary correlations in the residuals103—104 Dynamic models with variable intercepts, asymptotic covariance matrix derivation111—112 Dynamic models with variable intercepts, covariance estimator69—7071—72 Dynamic models with variable intercepts, fixed-effects models7295—103 Dynamic models with variable intercepts, fixed-effects vector autoregressive models105—111 Dynamic models with variable intercepts, initial conditions7085—8690—92 Dynamic models with variable intercepts, maximum likelihood estimator78—83 Dynamic models with variable intercepts, random-effects models73—92 Dynamic models, bias induced by315—316 Dynamic random-coefficient models175—180 Dynamic sample selection Tobit models265—267 Earnings dynamics example265 Economic distance310 Efficiency of estimates317—318 Elasticity estimates28—29 Electricity demand example172—173 Employment examples female193218—222 Employment examples income-schooling model113—114127—128136—138313 Employment examples truncated or censored data229—230 Employment examples unemployment theory216 Employment examples wage equations41—42 Endogenously determined sample selection model253—255 Error terms Chamberlain approach60—65 Error terms discrete-response models192—193206—207220 Error terms quadratic loss functions169 Error terms serially correlated57—59 Error terms simultaneous-equations models122—123126138 Error terms truncated and censored models226228 Error terms variable-coefficient models146153—155160167—170 Error-component three-stage least squares (EC2SLS) estimator126280 Error-component two-stage least squares (EC2SLS) estimator123126 Errors of measurement5304—309316 Estimation bias313—316 Europe, panel data sets from1—3 European Community Household Panel (ECHP)3319
Event histories328 Exogeneity, strict43—4449697095104203265 Exogeneity, weak95 Female employment examples193218—222 Filtering158 Fixed-effects models95—103 Fixed-effects models, discrete data194 199 Fixed-effects models, efficiency of the estimates317 Fixed-effects models, likelihood-based estimator and GMM relations99—101 Fixed-effects models, logit models327 Fixed-effects models, minimum-distance estimator98—99 Fixed-effects models, omitted variable bias314 Fixed-effects models, probit models198—199 Fixed-effects models, random-vs. fixed-effects specification101—103 Fixed-effects models, semiparametric two-step estimator253—255 Fixed-effects models, transformed likelihood approach96—98101—103 Fixed-effects models, truncated regression243—249 Fixed-effects models, vector autoregressive models105—111 Food demand example288—290 Gary income-maintenance project, attrition in238—240242 Gaussian quadrature formula201 Generalized method of moments (GMM) estimator kernel-weighted266—267 Generalized method of moments (GMM) estimator likelihood-based estimators and99—101 Generalized method of moments (GMM) estimator, measurement errors306—309 Generalized method of moments (GMM) estimator, random-effects models86—9095—96 Generalized method of moments (GMM) estimator, simple regression with variable intercepts60 Generalized method of moments (GMM) estimator, simulated294—295 Generalized method of moments (GMM) estimator, truncated or censored models264—265 Generalized method of moments (GMM) estimator, vector autoregressive models107—108 Generalized-least-squares (GLS) estimator dynamic random-effects models84—85323 Generalized-least-squares (GLS) estimator, multilevel structures303 Generalized-least-squares (GLS) estimator, rotating data281—282 Generalized-least-squares (GLS) estimator, simple regression with variable intercepts35—3845535558—59320 Generalized-least-squares (GLS) estimator, simultaneous-equations models117—118125—126 Generalized-least-squares (GLS) estimator, variable-coefficients models145—146154164170 Gibbs sampler177—178 Group membership matrices304 Growth-rate regression model6—7 Grunfeld investment function147 Hausman test of misspecification50—51102321 Hausman wage equations42 Hausman — Wise model of attrition237—240242 Heckman sample selection correction254 Heckman two-step estimator227230236241 Heckman — Willis model219221 Hermite integration formula201 Heterogeneity bias8—10 Heterogeneity female employment example218—222 Heterogeneity problems in tracing20—21 Heterogeneity state dependence and216—218222 Heteroscedasticity in random-effects models89 Heteroscedasticity in simple regression with variable intercepts models55—57 Heteroscedasticity in simultaneous-equations models124 Heteroscedasticity in single-equation structural models120122 Heteroscedasticity in truncated or censored models255 Heteroscedasticity in variable-coefficient models148156162 Heteroscedasticity individual320 Heteroscedasticity Lagrange-multiplier test148156162325 Heteroscedasticity unit-root tests299 Hierarchical structure302—304 Hildreth — Houck estimator325 Honore — Kyriazidou estimator223—224 Household brand choices example221—224 Housing expenditure example255—259 Identification dynamic random-coefficients models326 Identification triangular system of simultaneous equations127—129 Identification using prior structure of the lag coefficients275—277 Identification using prior structure of the process of the exogenous variable271—275 Incidental-parameters48—49819596107194—196204244 Income elasticity example285—286289 Income-schooling model113—114127—128136—138313 Incomplete panel data268—290 Incomplete panel data distributed lag estimation in short panels268—279 Incomplete panel data, food demand example288—290 Incomplete panel data, income elasticity example285—286289 Incomplete panel data, pooling of cross-section and time-series data285—290 Incomplete panel data, pseudopanels283—285 Incomplete panel data, rotating or randomly missing data279—283 Independence of irrelevant alternatives192 Individual time-invariant variables27 Individual time-varying variables27 Individual-mean corrected regression model16—17 Information matrix (IV)148—149197 Initial conditions common vs. difference means91 Initial conditions, dynamic discrete data models208—211 Initial conditions, dynamic models with variable intercepts7085—8690—91 Initial conditions, incomplete panel data283 Initial conditions, likelihood functions and90—92 Instrumental-variable (IV) estimator dynamic fixed-effects models100 Instrumental-variable (IV) estimator dynamic random-effects models85—8695—96 Instrumental-variable (IV) estimator purged, in triangular simultaneous-equations models130—133 Inverse gamma (IG) distribution investment functions analysis of covariance of21—26 Investment functions variable-coefficient models141—142147180—185 Investment functions, importance of increase in sales26 Joint limits approach296 Kalman filter158—161 Kernel density functions214231—233255 Kernel-weighted generalized method-of-moments (KGMM) estimator266—267 Koyck lag model276—277 Kronecker product of two matrices54321 Kyriazidou estimator253—255256266 Labor supply, life-cycle6 Lagged dependent variables707485 Lagrange-multiplier test for heteroscedasticity148156162325 Latent response functions225292 Latent variables127 Least-absolute deviation (LAD) estimator243—253 Least-squares dummy-variables (LSDV) dummy variables for omitted variables30 Least-squares dummy-variables (LSDV) dynamic panel data models71—72 Least-squares dummy-variables (LSDV) fixed-effects models30—33 Least-squares dummy-variables (LSDV) random-effects models37 Least-squares dummy-variables (LSDV) simultaneous-equations models118 Least-squares dummy-variables (LSDV) variable-coefficient models142 Least-squares estimatorsgeneralized-least-squares estimator joint generalized-least-squares estimation116—119 Least-squares estimators ordinary31—3373—74 Least-squares estimators, pairwise trimmed243—253 Least-squares estimators, symmetrically trimmed228—229 Least-squares estimators, three-stage6483124—126 Least-squares estimators, two-stage120—123 Least-squares estimators, variable-coefficient models146 Least-squares regression5—6 Lee estimator205—206 Likelihood functionsmaximum likelihood estimation Likelihood functions GMM and99—101 Likelihood functions pooled cross-sectional and time-series data286—290 Likelihood functions, conditional vs. marginal43—49 Likelihood functions, discrete-response models190—192194—198 Likelihood functions, dynamic discrete data models209—211 Likelihood functions, fixed effects models209 Likelihood functions, random-effects models199—202209 Likelihood functions, randomly missing data283 Likelihood functions, rotating samples280 Likelihood functions, testing initial condition hypotheses90—91 Likelihood functions, transformed approach96—98101—103 Likelihood functions, truncated and censored models226230237—238240—242 Limited-information principle120122 Linear regression296314 Linear-probability models189—190195—196 Liquidity constraints example180—185 Logistic distribution190 Logit models189—190195—198215222—223327 Long-haul long-distance service171—172 Manheim Innovation Panel (MIP)3 Manheim Innovation Panel—Service Sector (MIP-S)3 Manski maximum score estimator203—205212214 Manufacturing price equations150—151 Markov processes207—208210—211219—220327 Maximum likelihood estimation (MLE) bias simulation evidence91—93 Maximum likelihood estimation (MLE) consistency properties80 Maximum likelihood estimation (MLE) discrete data models191194—196217219
approach 
|
|
Î ïðîåêòå