Herding is the tendency of some polling firms to be influenced by others when issuing poll results. A pollster might want to avoid publishing a poll if it perceives that poll to be an outlier. Or it might have a poor methodology and make ad hoc adjustments so that its poll is more in line with a stronger one.
The closer the election gets, the harder it is to tell who is going to win, according to a poll released today showing the races for governor and the Senate effectively tied.
Democrat Michelle Nunn’s 47 percent gives her a slight lead in the Senate race over Republican David Perdue’s 45 percent, but the survey’s 4 percent margin of error means they’re statistically in a dead heat less than two weeks before Election Day. Libertarian Amanda Swafford’s 4 percent could trigger a January runoff by preventing Nunn from getting a majority. Another 4 percent haven’t made up their minds yet.
In the contest for governor, Republican Nathan Deal and Democrat Jason Carter each command 44 percent while Libertarian Andrew Hunt is taking 5 percent. Eight percent of those surveyed were still mulling over the choices.
The poll of 704 general-election voters was conducted by automated questionnaires via cellphone and landline Tuesday and Wednesday by InsiderAdvantage and Opinion Savvy on behalf of Morris News Service and Fox5. Pollsters weighted the responses to reflect an anticipated turnout where 37 percent of the voters are black and 55 percent are female.
The Georgia Democratic Party is engaged in vicious race-baiting in a divide and conquer strategy to drive African-American voters to the polls. The above photo originated, I believe, from an AJC scan, but has been traveling across the internet for 24 hours. (more…)
To calculate the unemployment rate, the U.S. Census Bureau and U.S. Bureau of Labor Statistics takes samples of nearly 60,000 households. They are surveyed monthly for four consecutive months, left alone for eight months and then surveyed again monthly for the next four months.
That means that in each month, there are eight “rotation groups,” each of them intended to be representative of the population. The government then weights the groups to come up with an official unemployment rate.
So that weighting has a large effect on the result.
Krueger and his collaborators found that during the first half of 2014, the unemployment rate among people in the first month of being interviewed was 7.5 percent. However, for those in the final month of being interviewed, it was only 6.1 percent.
But the Bureau of Labor Statistics weighted the first interview more heavily, so the official unemployment rate for this period was 6.5 percent.