Estimating the Effects of Intervention Into a Non-stationary Time-Series

Observation of a variable Z at several equally spaced points in time yields the observations z1, z2,..., ZN. Suppose that an intervention (T) is made at some point in time before time N into the process presumed to be controlling Z. The time-series is said to be interrupted at a point in time, say nl less than N: z1, ..., zn, T, zn + 1, ..., ZN. When the intervention is made for purposes of studying its effects, whether they be a change in level or direction, on the time-series, the pardigm is that of what has come to be called in educational research and the social