Stochastic apportionment

Abstract

The problem of how to allocate to states the seats in the US House of Representatives is the most studied instance of what is termed the `apportionment problem'. We propose a new method of apportionment which is stochastic, which meets the quota condition, and which is fair in the sense of expectations. Two sources of systematic unfairness are identified, firstly the lower bound condition (every state shall receive at least one seat), and secondly the lower quota condition (every state shall receive at least the integer part of its quota).