Robustness and fragility in Leamer's sense are defined with respect to a particular coefficient over a class of models. This paper shows that inclusion of the data generation process in that class of models is neither necessary nor sufficient for robustness. This result holds even if the properly specified model has well-determined, statistically significant coefficients. The encompassing principle explains how this result can occur. Encompassing also provides a link to a more common-sense notion of robustness, which is still a desirable property empirically; and encompassing clarifies recent discussion on model averaging and the pooling of forecasts.