Over dispersion is the phenomenon which occurs when empirical variance in the data exceeds the nominal variance under some supposed model. Most often encountered when the modeling data which occurs in the form of proportions or counts, where it is frequently observed that there is more variation than, for instance, an assumed binomial distribution can accommodate.
There might be a variety of relatively easy reasons of the amplified variation, ranging from the presence of one or more outliers, to the mis-specification of model being applied to the data. If none of these explanations could explain the phenomenon then it is likely that it is due to the variation between the response probabilities or correlation between the binary responses, in which case particular modelling procedures might be required.