Zogby: Obama back on top (single day lead of 10 points)

[pnwmom]

"One day is not a trend -- Obama holds his lead"

http://www.zogby.com/main.htm

UTICA, New York -- After a strong day of polling for Republican presidential candidate John McCain on Friday, Democrat Barack Obama experienced a strong single day of polling on Saturday, retaining a 5.7 point advantage that is right at the edge of the margin of error of the Reuters/C-SPAN/Zogby daily tracking poll. The race has remained remarkably stable down the stretch, this three-day rolling average poll shows.


Pollster John Zogby: "Obama has consolidated his lead over McCain. His single day lead today was back to 52%-42%. He leads by 10 among independents and has solidified his base. He leads among Hispanics by38 points, African Americans by 88, 18-24 year olds by 36, 18-29 year olds by 25, 25-34 year olds by 16, women by 8, and men by 3. He has a 17 point lead among those who have already voted, 22 by those who have registered to vote in the past 6 months, Moderates by 34, Catholics by 10. He even receives 21% support among Conservatives.

"So what happened to give McCain a one-point lead in the one-day polling on Friday? It was a day of consolidation for him, too. He had been losing support among key groups and began to regain some of his own base. He now leads by 21 points among NASCAR fans, 9 among investors, 6 among voters in armed forces households, and 2 among voters over 65 years old.

"Remember, as I said yesterday, one day does not make a trend. This is a three-day rolling average and no changes have been tectonic. A special note to blogger friends: calm it down. Lay off the cable television noise and look at your baseball cards in your spare time. It is better for your (and everyone else's) health."

SNIP

[johnnydrama]

3. the last laugh

Guess which day of polling will slide off the 3 day average during Zogby's last tracking poll Monday night.

haha

[RL3AO]

4. Thats strange. Its not the main headline on Drudge Report

what gives?

[MrMickeysMom]

7. This might go along with the comment I just made...

What are we now to believe?

There are no definitive news sources of polling data? Did they account for certain demographics?

[MrMickeysMom]

5. I swear to God that I heard a Fixed Nose round table this AM...

... I couldn't get away from it, as I was in a patients' room with Fox on. This panel member on Sat morning was talking about how McCain was ahead in the Zogby poll.

Which Zogby poll was she talking about? By the way, I joked that watching Fox news would rot your brain (my patient knows me well enough to have taken that with a smile).

[pnwmom]

1. Zogby does a 3 day rolling poll, with 400 voters each day, and adds the votes

together to make one poll of 1200 voters with about a 3% margin of error. However, each single day's polling is that much smaller with a significantly bigger margin of error.

For yesterday's single day poll results, Zogby did -- for whatever reason -- have McCain on top by 1 point. Today they had him down by 10 points. But given the large margin of error, even these differences don't count for much. And rolling the 3 days worth together, Zogby ends up with Obama on top by about 6 points -- which is close to where he's been all along.

[MrMickeysMom]

2. Is this usual?

I'm trying to follow what you described as "each single day's polling is that much smaller". Would this means it matters asking the same question from day to day due to people's state of mind being swayed that significantly... so each day should be a separate margin of error?

[pnwmom]

10. Each day's polling, if considered separately -- with 400 voters in each sample --

has its own separate margin of error. I don't know it off the top of my head, but it is significantly bigger than the MOE of the larger, combined 3-day poll (of 1200 voters in total).

I'm not sure I understand your question -- it isn't 400 people being asked 3 times and changing their minds. It's 1200 people being asked over 3 days, about 400 different people each day. Any time you have a much bigger sample, you have a smaller margin of error -- so the 1200 voter, 3 day cumulative poll is closer to being accurate than a single day 400 voter poll.

[MrMickeysMom]

12. I was trying to understand your explanation ...

It wasn't the same sample population being asked the question 3 times. It did seem like it was the same sample size being asked each day.

That being understood, each day's datum seemed to me to be affected by different "variables". What I mean by that is 400 different people would be processing their answers on that given day after being hit with commercials and marketing to the candidates.... news about the private information to reflect Obama's aunt was here illegally from Kenya, blah, blah, blah. So... I was thinking that these variable change day by day and affect individuals answers in the sample.

The soft science of polling seems wacky in how it changes from day to day, but the rolling average of this reflected more accurately that Obama was up by 6% points. I think that's what I understood you to say.

I was just trying to see if I understood this, since you probably follow this way more accurately than I do. :-)

[high density]

6. Zogby should be embarrassed for publishing this bullshit

His results are the most erratic in the industry. McCain +1 to Obama +10 in 24 hours?

[melody]

8. Zogby should be ashamed of himself

And I'm sure he's not.

[my3boyz]

9. Only by 6 with armed forces households? Mr. I will remind you that I'm a former POW

until I'm blue in the face McCain is only leading by 6?

[DCBob]

11. I had to laugh when I read this. Zogby has lost all credibility.

I suspect even Drudge will quit quoting to him. Meanwhile this means Obama is truly solidifying his lead. Now "all" polls have him moving up. This looks like a landslide of historic proportions coming on Tuesday.