Testing purchasing power parity: some evidence of the effects of transaction costs
研究发现测量误差和交易成本会严重干扰购买力平价的检验，导致传统检验在预测误差大时错误接受PPP、小时错误拒绝，并偏向于接受汇率与相对价格指数无协整的零假设。
Empirical tests of purchasing power parity often recognize the problems created by simultaneous equations, but seldom recognize the effects of measurement error or transaction costs. Presumably because most researchers believe that they are unimportant. We present evidence that shows that measurement error and transaction costs and create serious econometric problems for testing purchasing power parity. One effect of these problems is that conventional tests of purchasing power parity can accept PPP when predictive errors are relatively large and reject it when predictive errors are relatively small. Another effect is to bias test of cointegration toward accepting the null of no cointegration between exchange rates and relative price indexes. We also construct a simple model of the determination of exchange rates that shows how transaction costs lead to regression switiching.