Shrinkage Estimators for the Nonlinear Regression Model
In this paper, we discuss various large sample estimation techniques in a nonlinear regression model. We propose estimators on the basis of preliminary tests of significance and James-Stein rule. The properties of these estimators are studied in the problem of estimating regression coefficients in the multiple regression model when it is a priori suspected that the coefficients may be restricted to a subspace. <br> A simulation based on a demand for money model shows the superiority of the positive-part shrinkage estimator over a range of economically meaningful parameter values. This indicates that this estimator can be usefully employed in important practical situations.