Model Identification in Time-Series Analysis: Some Empirical Results.
William L. Padia · 1975
1 ABSTRACT Model identification stime-series data is essential to valid' statistical tests of interventIOneffects. Model identification is, at best, inexact iu the-todiat and, behavioral sciences'where onei.k often confnented with small: numbers of obstervations. These problems'gre discussed, iffid the resales of independent identifications of 130 social and behavioral time-series 111! by two judges'are presented. The majority (75 percent) of the series were represented by one of four *basic models: white noise independen.b.observations); first-order autoregressive; first-order moving averaged model in the first difference; -and white noise in the first difference. (AutAo4