The density functions analysis of and in misspecified linear regression models

نوع المستند : المقالة الأصلية

المؤلف

المستخلص

In this paper, we analyze the density functions of and the adjusted ( ) when there are two types of misspecification. The first is exclusion of relevant variables and the other is inclusion of irrelevant variables. It is shown numerically that both  and tends to underestimate when there are omitted variables, and both tend to overestimate when there are irrelevant variables.