Testing for Cointegration between House Prices and Economic Fundamentals
指出仅检验线性协整可能误判房价与基本面无关，通过两步法对10个美国城市分析，发现1个城市存在线性协整、6个存在非线性协整，剩余3个需进一步检验。
Economic theory predicts three possibilities for the cointegration relationship between house prices and economic fundamentals: linear cointegration, nonlinear cointegration and no cointegration. In contrast, the empirical literature has only examined linear cointegration. This article argues that ignoring nonlinear cointegration may lead to misleading conclusions that no cointegration exists between house prices and the fundamentals. To illustrate this point, I test for cointegration for ten U.S. cities and find that only one city shows evidence of linear cointegration. Further analysis using the two‐step testing procedure yields evidence of nonlinear cointegration for six other cities. Still, there are three cities left out without evidence of nonlinear cointegration. Further studies are needed to test for other forms of nonlinear cointegration before a conclusion of no cointegration can be reached for the remaining three cities.