Content deleted Content added
Made the description more general. Unit root tests don't all have to rely on autoregressive model, even if most do |
No edit summary |
||
Line 1:
In [[statistics]], a '''unit root test''' tests whether a [[time series]] variable is non-stationary and possesses a [[unit root]]. The null hypothesis is generally defined as the presence of a unit root and the alternative hypothesis is either [[Stationary process|stationarity]], [[Trend stationary|trend stationarity]] or explosive root depending on the test used.
== General approach ==
Line 22:
Other popular tests include:
* [[Phillips–Perron test]]
* [[KPSS test]] (in which the null hypothesis is [[Trend stationary|trend stationarity]] rather than the presence of a [[Stationary process|
* [[ADF-GLS test]]
* [[Zivot–Andrews test]]
| |||