Estimation of Regression Coefficients Subject to Exact Linear Restrictions when Some Observations are Missing and Quadratic Error Balanced Loss Function is Used

• Autores: H. Toutenburg
• Localización: Test: An Official Journal of the Spanish Society of Statistics and Operations Research, ISSN-e 1863-8260, ISSN 1133-0686, Vol. 14, Nº. 2, 2005, págs. 385-396
• Idioma: inglés
• DOI: 10.1007/bf02595409
• Texto completo no disponible (Saber más ...)
• Resumen

  • This article considers a linear regression model when a set of exact linear restrictions binding the coefficients is available and some observations on the study variable are missing. Estimators for the vectors of regression coefficients are presented and their superiority properties with respect to the criteria of the variance covariance matrix and the risk under balanced loss functions are analyzed.