Editing Highest averages method (section)

=== Bias ===
There are many metrics of [[seat bias]]. While the Webster method is sometimes described as "uniquely" unbiased,<ref name="Balinski-1980" /> this uniqueness property relies on a [[Bias of an estimator|technical definition of bias]], which is defined as the [[Expected value|average]] difference between a state's number of seats and its [[Entitlement (fair division)|seat entitlement]]. In other words, a method is called unbiased if the number of seats a state receives is, on average across many elections, equal to its seat entitlement.<ref name="Balinski-1980" />

By this definition, the Webster method is the least-biased apportionment method,<ref name="Pukelsheim-2017-2" /> while Huntington-Hill exhibits a mild bias towards smaller parties.<ref name="Balinski-1980" /> However, other researchers have noted that slightly different definitions of bias, generally based on [[Percent error|''percent'' errors]], find the opposite result (The Huntington-Hill method is unbiased, while the Webster method is slightly biased towards large parties).<ref name="Pukelsheim-2017-2" /><ref name="Ernst-1994" />

In practice, the difference between these definitions is small when handling parties or states with more than one seat.<ref name="Pukelsheim-2017-2" /> Thus, both the Huntington-Hill and Webster methods can be considered unbiased or low-bias methods (unlike the Jefferson or Adams methods).<ref name="Pukelsheim-2017-2" /><ref name="Ernst-1994" /> A 1929 report to Congress by the [[National Academy of Sciences]] recommended the Huntington-Hill method,<ref name="Huntington-1929" /> while the [[Supreme Court of the United States|Supreme Court]] has ruled the choice to be a matter of opinion.<ref name="Ernst-1994" />