Bases for alternative nonparametric Mincer function

Autores/as

  • Alejandro Brondino Consultor Independiente
  • Matias Nicolas Sacoto Molina Universidad de Cuenca

DOI:

https://doi.org/10.25097/rep.n25.2017.02

Palabras clave:

Non parametric econometrics, statistical inference, non parametric estimation, Mincer function, confidence intervals.

Resumen

This work undertakes a nonparametric regression in order to model a simplified Mincer Function of earnings. The main advantages of using this technique is that it does not rely on assumptions and the statistical inference is not sensitive to distributions disturbances due to violations of the assumptions. The results of the nonparametric estimation are compared to a classical OLS regression. From this comparison it was found that the OLS estimator did not fulfilled the assumptions that this method requires, therefore, the statistical inference from this estimation is misleading. On the other hand, the confidence intervals obtained from the nonparametric regression are more accurate and less sensitive to variability and magnitude of the variables. Consequently, the nonparametric estimation would be an alternative to model labor market variables avoiding string assumptions that will lead to wrong statistical inference conclusions.

Descargas

Los datos de descargas todavía no están disponibles.

Biografía del autor/a

Alejandro Brondino, Consultor Independiente

Licenciado en Economía

MSc Ecoometrics

Consultor Independiente de modelado Econométrico.

Matias Nicolas Sacoto Molina, Universidad de Cuenca

Economista

MSc Econometrics, Specialization in Financial Econometrics.

Docente de: Estadística I, Matemáticas II y III, Econometría I, en la Universidad de Cuenca.

Descargas

Publicado

2017-01-06

Cómo citar

Brondino, A., & Sacoto Molina, M. N. (2017). Bases for alternative nonparametric Mincer function. Revista Economía Y Política, (25), 29–43. https://doi.org/10.25097/rep.n25.2017.02

Número

Sección

Artículos