ERIC Number: ED110463
Record Type: RIE
Publication Date: 1975-Apr
Reference Count: 0
Model Identification in Time-Series Analysis: Some Empirical Results.
Padia, William L.
Model identification of time-series data is essential to valid statistical tests of intervention effects. Model identification is, at best, inexact in the social and behavioral sciences where one is often confronted with small numbers of observations. These problems are discussed, and the results of independent identifications of 130 social and behavioral time-series by two judges are presented. The majority (75 percent) of the series were represented by one of four basic models: "white noise" (i.e., independent observations); first-order autoregressive; first-order moving averages model in the first difference; and "white noise" in the first difference. (Author)
Publication Type: Reports - Research
Education Level: N/A
Authoring Institution: N/A
Note: Paper presented at the Annual Meeting of the American Educational Research Association (Washington, D.C., March 30-April 3, 1975)