Effects of data aggregation on the power of tests for a unit root : A simulation study

This paper studies the effects of data aggregation on the powers of the Phillips-Perron and augmented Dickey-Fuller tests for a unit root by simulation. It is shown that using the data generated by aggregating subinterval data results in lower powers of the tests. In addition, especially for the aggregate data, the Phillip-Perron tests appear to be more powerful than the augmented Dickey-Fuller test in finite samples, according to our experimental format.