Journal of Statistical Software (Oct 2013)
Costationarity of Locally Stationary Time Series Using costat
Abstract
This article describes the R package costat. This package enables a user to (i) perform a test for time series stationarity; (ii) compute and plot time-localized autocovariances, and (iii) to determine and explore any costationary relationship between two locally stationary time series. Two locally stationary time series are said to be costationary if there exists two time-varying combination functions such that the linear combination of the two series with the functions produces another time series which is stationary. Costationarity existing between two time series indicates a relationship between the series that might be usefully exploited in a number of ways. Sometimes the relationship itself is of interest, sometimes the derived stationary series is of interest and useful as a substitute for either of the original stationary series in some applications.