Should Barack Obama worry about the Bradley effect? The much-discussed effect refers to observed discrepancies between voter opinion polls and election outcomes, in which African-American candidates receive a smaller vote share than would be predicted using opinion polls. In this column, I study US congressional and gubernatorial contests from 1998 to 2006 � black candidates on average receive a 2-3% lower share of the two-party vote than non-black candidates with similar numbers in the polls. If an effect of a similar size would appear in the current presidential race, then it would lower Obama�s probability of winning from 85% to 53%. However, black Republican candidates drive the result, so it may not apply to Obama�s campaign.

David Stromberg at VoxEU today. What makes the effect interesting is that he corrects for the idea that most estimates of the effect miss the confounding factor that most black candidates for governor or Congress have less than 50% poll support. (The two effects would work against each other so that you'd find no significant Bradley effect.) Stromberg corrects for this by including the last poll result as a control variable.

...in the sub-sample of close elections, where the black candidate has 45-55% in the polls, the mean difference between elections and polls is �3.5%. The gap is �2.3% in races where the black candidate polls between 40-60%. Absent the catch-up effect, the black candidates do worse than the polls.

If you use the entire sample, Obama pulls 51-52% of the two-party vote based on Stromberg's estimates. If you buy the 55-45 spread instead, every poll with Obama under 53% becomes a plausibly a case for McCain. Looking at the RCP average, McCain would need all that and most of the remaining undecideds for an upset win. Current InTrade odds put Obama at 90%. A gambling man would bet the dog, and I'm such a man.

Labels: economics, elections