Estimating the LQAC model with I(2) variables
提出一种方法，用于在目标变量和部分驱动变量为I(2)过程时估计和检验线性二次调整成本模型，并利用英国货币需求数据进行了实证应用。
Tom ENGSTEDDepartment of Information Science, Aarhus School of Business, DK-8210 Aarhus V, andCentre for Non-linear Modelling in Economics, Aarhus University, Denmark.Niels HALDRUPDepartment of Economics, and Centre for Non-linear Modelling in Economics, AarhusUniversity, DK-8000 Aarhus C, Denmark.Abstract.This paper derives a method for estimating and testing the Linear Quadratic AdjustmentCost (LQAC) model when the target variable and some of the forcing variables follow I(2)processes. Based on a forward-looking error-correction formulation of the model it isshown how to obtain strongly consistent estimates of the structural long-run parametersand the adjustment cost parameter from both a linear and a non-linear cointegratingregression, where first-differences of the I(2) variables are included as regressors(multicointegration). Further, based on the estimated parameter values, it is shown how totest and evaluate the LQAC model using a VAR approach. In an empirical applicationusing UK money demand data, the non-linear multicointegrating regression delivers aneconomically plausible estimate of the adjustment cost parameter. However, the exactrestrictions implied by the LQAC model under rational expectations are strongly rejected.JEL-codes: C10, C12, C32, E24Keywords: Adjustment costs, error correction, money demand, rational expectations,multicointegration.This work was completed while the second author was visiting the Department forEconomics at University of California, San Diego, during fall, 1995. The hospitality of theDepartment is gratefully acknowledged. We would like to thank Pierre Siklos fordiscussions.