C STATISTIC POWER ANALYSIS THROUGH SIMULA TION

The (C) under bar statistic (Young, 1941) constitutes a suitable analy sis alternative for interrupted brief or short-time series used in beh avioral designs. For this reason, a Monte Carlo simulation study is ca rried out to determine the statistical power of the (C) over bar stati stic for each of the usage strategies proposed by Tryon (1982). The se ries generated allow to evaluate the limitations of the C statistic an d to compare the three possible analysis alternatives when the baselin e phase shows a trend, for different change patterns (i.e. comparison of series using the regression technique, comparison of series with di rect data, and analysis of the set of phases).