17 Simultaneous Equation Models Identification外文电子书籍.pdfVIP

Economics 140A Identification in Simultaneous Equation Models Simultaneous Equation Models Our second extension of the classic regression model, to which we devote two lectures, is to a system (or model) of more than one equation. Together, the equations describe the simultaneous evolution of multiple endogenous variables and are termed simultaneous equation models. Up to this point, we have considered structures in which only one variable, the dependent variable, is endogenous. We often think of the regressors as causing the movements in the dependent variable in that the regressors can be condi- tioned upon when studying the dependent variable. In many cases of interest to economists the conditional structure of a single equation breaks down, as two or more quantities are jointly determined. Perhaps the simplest such structure is to consider price and quantity for a speci脰c market (e.g. Vans tennis shoes in Santa Barbara). One might think of the following structure P = + Q + U ; t 0 1 t t where Pt is the price of a pair of shoes in period-t and Qt is the quantity of shoes sold in the corresponding period. Without question, the price of shoes is a搂ected by the quantity available. Surplus inventories are sold at discount and goods in short supply often sell at a premium. Yet, unless the Santa Barbara market forms only a tiny portion of total supply, the price at which the shoes are sold a搂ects the quantity. Shoes sold at discount re谩ect excess inventories and indicate that production should fall, the converse holds for shoes sold at a premium. If the regressor is also a function of the dependent variable, it is clear