-
Views
-
Cite
Cite
MANI Y. LAKSHMINARAYANAN, RICHARD F. GUNST, Estimation of parameters in linear structural relationships: Sensitivity to the choice of the ratio of error variances, Biometrika, Volume 71, Issue 3, December 1984, Pages 569–573, https://doi.org/10.1093/biomet/71.3.569
- Share Icon Share
Abstract
Maximum likelihood estimation of parameters in linear structural relationships under normality assumptions requires knowledge of one or more of the model parameters if no replication is available. The most common assumption added to the model definition is that the ratio of the error variances of the response and predictor variates is known. This paper investigates the use of asymptotic formulae for variances and mean squared errors as a function of sample size and the assumed value for the error variance ratio.