Estimation of quantile regressions with fixed effects

• Rios-Avila, Fernando ^[2] ; Ramos, Andrey ^[3] ; Canavire-Bacarreza, Gustavo ^[4] ; Siles, Leonardo ^[1]
  1. [1] Universidad de Chile

     Universidad de Chile

     Santiago, Chile

     
  2. [2] Universidad Privada Boliviana La Paz, Bolivia, and London School of Economics and Political Science London, UK
  3. [3] Bank of Spain Madrid, Spain
  4. [4] The World Bank Washington, DC, and Universidad Privada Boliviana La Paz, Bolivia

  Mostrar afiliaciones +
• Localización: The Stata journal, ISSN 1536-867X, Vol. 26, Nº. 1, 2026, págs. 111-131
• Idioma: inglés
• DOI: 10.1177
• Enlaces
  • Texto completo
• Resumen

  • In this article, we introduce two new commands, qregfe and qregplot, that are designed for fitting and visualizing quantile regression models with fixed effects. qregfe provides a unified syntax for implementing three panel-data estimators that are commonly used in empirical research: 1) the correlated random-effects specification of Abrevaya and Dahl (2008, Journal of Business and Economic Statistics 26: 379–397); 2) the two-step location-shift estimator of Canay (2011, Econometrics Journal 14: 368–386); and 3) the method of moments quantile regression approach of Machado and Santos Silva (2019, Journal of Econometrics 213: 145–173). The companion command qregplot produces coefficient–quantile plots, allowing researchers to visualize how the coefficients of each covariate change across the outcome conditional distribution.