Ickestationär

Ickestationär is not a standard term in statistics or econometrics. In formal usage, the likely intended concept is nichtstationär or non-stationary, referring to processes whose statistical properties change over time. If encountered, ickestationär is often a misspelling, informal variant, or a neologism, and should be clarified with the source.

A time series is considered stationary when its essential characteristics—such as the mean, variance, and autocovariance—do not depend on the time at which the series is observed. In practice, statisticians distinguish between weak (or second-order) stationarity and strong stationarity. Weak stationarity requires constant mean, constant variance, and autocovariances that depend only on the lag, not on time. Strong stationarity requires the entire distribution to be time-invariant. Non-stationary (nichtstationär) processes violate these conditions in various ways, often showing trends, changing variance, or evolving autocorrelation.

Common forms of non-stationarity include trend non-stationarity, where a deterministic trend explains the time evolution, and difference non-stationarity, typically indicated by a unit root, meaning the series behaves like a random walk. Non-stationary data are common in economics and climate series, such as gross domestic product, prices, or temperature records.

Detecting non-stationarity typically involves visual inspection, statistical tests for unit roots (for example, augmented Dickey–Fuller, Phillips–Perron), and tests for cointegration when multiple series are involved. Handling non-stationarity depends on its nature: detrending or transformation can render a series trend-stationary, differencing can remove a unit root, and cointegration can justify long-run relationships with error-correction models.

In summary, while ickestationär is not a recognized technical term, it most likely refers to non-stationarity, a central concern in time series analysis that shapes modeling, inference, and forecasting.