ABSTRACT
For many regression models and time series models that assume normality of the noise distribution, least squares estimates often coincide with or provide good approximations to the maximum likelihood estimates of the unknown parameters. This chapter explains the Householder transformation as a convenient method to obtain least squares estimates of regression models. It obtains precise estimates of the coefficients of the model and perform order selection or variable selection based on the information criterion Akaike Information Criterion quite efficiently. The maximum likelihood estimates of the regression coefficients of linear regression models can be obtained by the least squares method that minimizes. The function lsqr of the package Trigonometric regression model fits the regression model by the least squares method based on Housholder transformation.
