As usual, the folks at Pollster.com have put together an impressive analysis of the Survey USA data. In particular, they draw on the notion of statistical significance to classify states as strongly for a candidate, leaning towards that candidate, or toss-up.
Pollster.com: SurveyUSA’s 50 States with Sampling Error:
SurveyUSA colors in states on their maps even if a candidate leads by a point or two, margins that are not close to achieving statistical significance. However, since SurveyUSA says they did 600 interviews in each state, we can take their analysis a step further, applying statistical sampling error to the candidates’ margins in each state.
Professor Franklin and I have done just that, classifying each state based on the statistical significance of the candidate’s lead. We call a state “strong” for the candidate if they lead by a margin that is statistically significant at a 95% level of confidence, the level typically used to calculate the “margin of error” attached to most surveys. We label as “lean” any state where a candidate leads by more than one standard deviation, which amounts to a 68% confidence level. We label all other states as toss-ups.
Details below the cut.
Here are the money charts:
And more details on the numbers, sorting the states so you can compare where Clinton and Obama are strong:
An important caveat, beyond the usual (sampling error, polling registered not likely voters, polling so far in advance of an election, etc.) when looking at any poll:
Finally, keep in mind that since we are looking at 100 tests (2 each in 50 states), these results probably misclassify five states by chance alone (as opposed to the way we would classify them if SurveyUSA had called every working telephone in the 50 states).
In any event, I’m glad to see this massive Survey USA dataset (some 30,000 phone interviews) being put to good use by the best in the political blogosphere (gosh, it’s hard to let myself type that word. So it goes, that ship has sailed). I don’t think I have too much to add, except that this data would seem to support the Obama electability arguments, though other interpretations are possible. I wish they’d done more with the paired comparison (looking at how Obama did vs. how Clinton did), as I tried to do in my last post, as I know they could get some really interesting results out of it. Oh well, perhaps next time.
One more post on the election coming up, as promised but undelivered: Why Michigan and Florida should not be seated, and why it would be disrespectful to the voters in those states to do so.