NBER-NSF Time Series Conference; University of California at Davis, USA

Abstract for "A frequency domain approach to testing for second order stationarity" by Suhasini Subba Rao

We consider a test for second order stationarity based on the Discrete Fourier Transform (DFT). For stationary time series, the DFT at the fundemental frequencies is asymptotically uncorrelated, however this property does not necessarily hold for second order nonstationary time series. We use this property to construct the test statistic. We obtain the asymptotic sampling properties of the test statistic under the null and the alternative of local stationarity. We conduct a simulation study and illustrate our method with real life data examples, for example monthly temperature anomalies from 1900-present.

This is joint work with Yogesh Dwivedi, who is currently a PhD student.