Zurück zu den Preprints des Jahres 2009


2009-26

Optimal Design for Linear Regression Models in the Presence of Heteroscedasticity Caused by Random Coefficients

by Graßhoff, U., Doebler, A., Holling, H., Schwabe, R..


Series: 2009-26, Preprints

MSC:
62K05 Optimal designs
62J05 Linear regression

Abstract:
Random coefficients may result in a heteroscedasticity of observations. For particular situations, where only one observation is available per individual, we derive optimal designs based on the geometry of the design locus.

Keywords:
optimal design, random coefficient regression, linear mixed model, heteroscedastic linear model, geometry of design locus