Causal Inference with Spatially Disaggregated Data: Some Potentials and Limits

In studies of civil strife, the ecological fallacy seems to befall all large-$n$ studies and thus there has been a big push, by several researchers, in recent years to gather disaggregated, spatially explicit data. However, while such efforts are heroic and are likely to lead to better information, we find that the resulting data can not be analysed in conventional ways, if the estimation of causal effects is the goal. The reason is that such data brings about other dangers: the violation of the Stable Unit Treatment Value Assumption (SUTVA). To be specific, one ``treated'' group's enemy could hardly be its control. We get around this problem by changing the causal effect of interest and by carefully re-aggregating the lower level data so as to preserve its most salient information. Restricting our analysis to groups that are excluded from power, we find some tentative evidence that such groups are less likely to engage in conflict if they are more spatially integrated with other groups.