Throughout the election I have followed the statewide races at Pollster.com, starting my morning by checking their map of the country and electoral counts to see how the election is shaping up. Well, today they have turned Florida, Colorado, and Ohio BLUE! Or light blue, that is, for leaning towards Obama. For weeks there have been approximately ten "tossup" states shown in yellow, including Florida, Ohio, New Mexico, New Hampshire, etc. At times even states like Minnesota and Michigan were too close to call and shown in yellow by Pollster.com. When the polls in a respective state start to clearly trend to one candidate over the other it is turned light blue or light red. This is what happened today with Florida, Colorado, Ohio, and New Hampshire. None of the remaining tossup states have gone Democrat in a very long time: Nevada, Indiana, North Carolina, Virginia, and Missouri.
It is still a little too early for the polls to have picked up any trends and determine if McPalin’s turn to the dark side with their step up in negative adds has had an affect yet, but lets hope these favorable trends for Obama continue. We all know what they say about negative adds. See all that blue below the jump along with how Pollster.com does their numbers.
Look at all that blue:
Below I have cut and pasted from the Pollster.com FAQ's page so you can see where the numbers come from. They use a trending system to decide how to categorize each state and assign it a color:
Where do the numbers come from?
When you hold the mouse pointer over a state, you see a display of the latest "trend estimate" numbers from our charts of all available public polls for that race. The numbers for each candidate correspond to the most recent trend estimate -- that is the end point of the trend line that we draw for each candidate.
In most cases, the numbers are not an "average" but rather regression based trendlines. The specific methodology depends on the number of polls available.
If we have at least 8 public polls, we fit a trend line to the dots represented by each poll using a "Loess" iterative locally weighted least squares regression.
If we have between 4 and 7 polls, we fit a linear regression trend line (a straight line) to best fit the points.
If we have 3 polls or fewer, we calculate a simple average of the available surveys.
This is very good news for Obama!
The following is more on how the trends are configured. From my reading here, by using their trend system instead of an average of recent polls, their system would pick up movement in the polls a little faster. Thus, I hope McPalin's negativity is not going to work. But we will have to wait and see.
How do regression trend lines differ from simple averages?
Charles Franklin, who created the statistical routines that plot our trend lines, provided the following explanation last year:
Our trend estimate is just that, an estimate of the trends and where the race stands as of the latest data available. It is NOT a simple average of recent polling but a "local regression" estimate of support as of the most recent poll. So if you are trying to [calculate] our trend estimates from just averaging the recent polls, you won't succeed.
Here is a way to think about this: suppose the last 5 polls in a race are 25, 27, 29, 31 and 33. Which is a better estimate of where the race stands today? 29 (the mean) or 33 (the local trend)? Since support has risen by 2 points in each successive poll, our estimator will say the trend is currently 33%, not the 29% the polls averaged over the past 2 or 3 weeks during which the last 5 polls were taken. Of course real data are more noisy than my example, so we have to fit the trend in a more complicated way than the example, but the logic is the same. Our trend estimates are local regression predictions, not simple averaging. If the data have been flat for a while, the trend and the mean will be quite close to each other. But if the polls are moving consistently either up or down, the trend estimate will be a better estimate of opinion as of today while the simple average will be an estimate of where the race was some 3 polls ago (for a 5 poll average-- longer ago as more polls are included in the average.) And that's why we estimate the trends the way we do.