A Comparison of Asymptotic Covariance Matrices of Adjusted Least Squares and Structural Least Squares in Error Ridden Polynomial Regression

Kukush, Alexander und Schneeweiß, Hans (2000): A Comparison of Asymptotic Covariance Matrices of Adjusted Least Squares and Structural Least Squares in Error Ridden Polynomial Regression. Sonderforschungsbereich 386, Discussion Paper 218

Abstract

A polynomial structural errors-in-variables model with normal underlying distributions is investigated. An asymptotic covariance matrix of the SLS estimator is computed, including the correcting terms which appear because in the score function the sample mean and the sample variance are plugged in. The ALS estimator is also considered, which does not need any assumption on the regressor distribution. The asymptotic covariance matrices of the two estimators are compared in border cases of small and of large errors. In both situations it turns out that under the normality assumption SLS is strictly more efficient than ALS.

• Dokumententyp: Paper
• Keywords: Polynomial regression; structural errors-in-variables model; asymptotic covariance matrix; efficiency
• Fakultät: Mathematik, Informatik und Statistik > Statistik > Sonderforschungsbereich 386 ; Sonderforschungsbereiche > Sonderforschungsbereich 386
• Themengebiete: 500 Naturwissenschaften und Mathematik > 510 Mathematik
• Sprache: Englisch