Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Modèle à effets aléatoires sur données de panel× | Modèle à effets fixes× | |
|---|---|---|
| Domaine | Économétrie | Économétrie |
| Famille | Regression model | Regression model |
| Année d'origine≠ | 1966 | 1971–1978 |
| Auteur d'origine≠ | Balestra & Nerlove | Mundlak (1978); Nerlove (1971); classical panel econometrics |
| Type≠ | Panel data estimator | Panel regression estimator |
| Source fondatrice≠ | Balestra, P., & Nerlove, M. (1966). Pooling cross section and time series data in the estimation of a dynamic model: The demand for natural gas. Econometrica, 34(3), 585–612. DOI ↗ | Baltagi, B. H. (2021). Econometric Analysis of Panel Data (6th ed.). Springer. ISBN: 978-3030538002 |
| Alias | random effects estimator, RE model, GLS random effects, error components model | FE model, within estimator, least squares dummy variable, LSDV regression |
| Apparentées | 5 | 5 |
| Résumé≠ | The panel random effects (RE) model treats individual-specific effects as random draws from a population distribution rather than fixed constants, enabling efficient estimation by generalised least squares and allowing inference about time-invariant regressors that are swept away in fixed effects estimation. | The fixed effects (FE) model is the workhorse estimator for panel data when unobserved unit-specific characteristics are suspected to correlate with the regressors. By absorbing each entity's time-invariant heterogeneity into a separate intercept, FE isolates the causal effect of within-unit variation and eliminates omitted-variable bias from time-constant confounders. |
| ScholarGateJeu de données ↗ |
|
|