When is a polity biased? Consider an “outsider” who observes policy data but observes neither citizens’ preferences nor the underlying distribution of political power. He views political power as if it were derived from wealth-weighted voting, where the weights determine the wealth bias. Positive weights favor the rich whereas negative ones favor the poor. We show that any policy data is rationalized by any wealth-weighted system. However, policy and polling observations together imply explicit bounds on the set of rationalizing biases. Accumulated data narrows this band. The inferential model is consistent with models of political competition for campaign contributions.