A simple technique for directly testing the parameters of a time-series regression model for instability across frequencies is presented. The method can be implemented easily in the time domain, so that parameter instability across frequency bands can be conveniently detected and modeled in conjunction with other econometric features of the problem athand, such as simultaneity, cointegration, missing observations, andcross-equation restrictions. The usefulness of the newtechnique is illustrated with an application to a cointegratedconsumption-income regression model, yielding a straightforwardtest of the permanent income hypothesis.