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)