Empirical evidence of least squares in the Random Coefficients Regression Model

• Autor: Huamanchumo de la Cuba, Luis
• Formato: artículo
• Fecha de Publicación: 2001
• Institución: Universidad Nacional de Ingeniería
• Repositorio: Revistas - Universidad Nacional de Ingeniería
• Lenguaje: español
• OAI Identifier: oai:oai:revistas.uni.edu.pe:article/527
• Enlace del recurso: https://revistas.uni.edu.pe/index.php/tecnia/article/view/527
• Nivel de acceso: acceso abierto
• Materia: Coeficientes Aleatorios; Mínimos Cuadrados Generalizados; Sesgo; Consistencia; Eficiencia; Random Coefficients; Generalized Least Squares; Bias; Consistency; Efficiency

This article studies some properties in finite samples of several estimators of the Mean Response Coefficient in a Linear Regression Model of Random Coefficients.For this purpose, it was necessary to design a sample experiment. Thus, evidence about Bias, Consistency and Efficiency was obtained from 15,120 estimates. According to this, not only the Two-Stage Generalized Least Squares (GLS) estimator produced the best results but also the Ordinary Least Squares (OLS) estimator by obtaining significant gains in Efficiency when it was estimated from a model without Error of Specification. It is necessary to expand this research by including the Maximum Likelihood estimator.