Fiche du document
- handle: 10670/1.5tgulh
- halshs: halshs-01719835
info:eu-repo/semantics/OpenAccess
Mots-clés
Time-invariant variables Panel data Time-series cross-sections Pretest estimator Mundlak estimator Hausman-Taylor estimator C - Mathematical and Quantitative Methods/C.C1 - Econometric and Statistical Methods and Methodology: General C - Mathematical and Quantitative Methods/C.C2 - Single Equation Models • Single Variables/C.C2.C22 - Time-Series Models • Dynamic Quantile Regressions • Dynamic Treatment Effect Models • Diffusion Processes C - Mathematical and Quantitative Methods/C.C2 - Single Equation Models • Single Variables/C.C2.C23 - Panel Data Models • Spatio-temporal ModelsSujets proches
Hours (Time) Squares, Least Method of least squares Pattern ModelCiter ce document
Jean-Bernard Chatelain et al., « Inference on time-invariant variables using panel data: a pretest estimator », HAL-SHS : économie et finance, ID : 10670/1.5tgulh
Métriques
Partage / Export
Résumé
For static panel data models that include endogenous time-invariant variables corre- lated with individual e¤ects, exogenous averages over time of time-varying variables can be internal instruments. To pretest their exogeneity, we .rst estimate a random e¤ects model that includes all averages over time of time-varying variables (Mundlak, 1978; Kr- ishnakumar, 2006). Internal instruments are then selected if their parameter is statistically di¤erent from zero (Mundlak, 1978; Hausman and Taylor, 1981). Finally, we estimate a Hausman-Taylor (1981) model using these internal instruments. We then evaluate the bi- ases of currently used alternative estimators in a Monte-Carlo simulation: repeated between, ordinary least squares, two-stage restricted between, Oaxaca-Geisler estimator, .xed e¤ect vector decomposition, and random e¤ects (restricted generalized least squares).