The Integrated Moving Average (IMA) model of time series, and the analysis of intervention effects based on it, assume random shocks which are normally distributed. To determine the robustness of the analysis to violations of this assumption, empirical sampling methods were employed. Samples were generated from three populations; normal, moderately non-normal, and severely non-normal. The samples were combined with values of other quantities in the model, the resulting "observations" subjected to time-series analysis, and the effect on empirical significance levels noted. The analysis of interventions based on the IMA model was robust to violations of the normality assumption. (Author)