A nonstationary time series is a time series that is not a stationary time series. In particular,
strict stationarity fails if the joint distribution
of
changes when all time indices are shifted by the same amount. Weak
stationarity fails if the mean depends on time or if the covariance
depends on the observation times rather than only on their lag.
Time-dependent trends, changing variances, and unit roots are common sources of nonstationarity. Some nonstationary series can be transformed
to stationarity by detrending or by applying the difference
operator.
changes when all time indices are shifted by the same amount. Weak
stationarity fails if the mean depends on time or if the covariance
depends on the observation times rather than only on their lag.
