Rasmussen NH and IA: Obama leads

[Rowan]

RAS NH
Obama 50%(-3)
McCain 46%(+3)

RAS IA
Obama 52%(+1)
McCain 44%(+1)

[Fmr. Pres. Duke]

I'm surprised Iowa is that close after McCain railed against the ethanol farmers. New Hampshire is tightening just at the right time.

[TheresNoMoney]

New Hampshire is tightening just at the right time.

I doubt that NH is tightening, there's no reason it would be. Probably statistical noise.

[Rowan]

New Hampshire is tightening just at the right time.

I doubt that NH is tightening, there's no reason it would be. Probably statistical noise.

A 6 point swing isn't statistical noise.

[Josh/Devilman88]

New Hampshire is tightening just at the right time.

I doubt that NH is tightening, there's no reason it would be. Probably statistical noise.

A 6 point swing isn't statistical noise.

Very good numbers for McCain today. I still would like to know if Rasy put early voter into the polls.

[Rococo4]

these look right to me

[ChrisFromNJ]

these look right to me

No they don't.

Particularly New Hampshire.

[J. J.]

I'm surprised about IA, but I've thought NH will be close.

[Alcon]

New Hampshire is tightening just at the right time.

I doubt that NH is tightening, there's no reason it would be. Probably statistical noise.

A 6 point swing isn't statistical noise.

Sure it could be.  The MoE on this poll is something like +/-3.5%, right?  That swing is within MoE.  That means that it doesn't reach statistical significance at the 95th confidence level.  Does that mean it's probably noise?  No, but it could be.  Anything could be, at a given confidence rate.  Optimism is fine I guess, dude, but strive a little harder for intellectual honesty.

[Brittain33]

I can't imagine why Sarah Palin would want to spend so much time in these two states when they're unlikely to vote for McCain and aren't key for a 2008 victory.

[Rococo4]

these look right to me

No they don't.

Particularly New Hampshire.

yes sir

[Rowan]

New Hampshire is tightening just at the right time.

I doubt that NH is tightening, there's no reason it would be. Probably statistical noise.

A 6 point swing isn't statistical noise.

Sure it could be.  The MoE on this poll is something like +/-3.5%, right?  That swing is within MoE.  That means that it doesn't reach statistical significance at the 95th confidence level.  Does that mean it's probably noise?  No, but it could be.  Anything could be, at a given confidence rate.  Optimism is fine I guess, dude, but strive a little harder for intellectual honesty.

Okay, what I should have said was that more than likely it's not statistical noise. Better?

[TheresNoMoney]

Brandon, can you post the internals for the NH poll?

[Alcon]

Okay, what I should have said was that more than likely it's not statistical noise. Better?

I guess.  Honestly I don't know at what point something becomes less likely to be statistical noise.  The 50% confidence interval, I guess?  Not sure when that's reached.  Wish there were a calculator for that.

I was just pointing out being concretely sure it isn't statistical noise when it's within the 95th confidence interval is a bit dangerous.  Methodology/sampling errors + statistical noise = a lot of uncertainty, maybe 1-in-7 polls or something like that.  But, yeah, better, def.

[Rowan]

Brandon, can you post the internals for the NH poll?

Scotty Ras doesn't release the internals until 5 PM.

[cinyc]

New Hampshire is tightening just at the right time.

I doubt that NH is tightening, there's no reason it would be. Probably statistical noise.

Ras takes a lot of his polls on one day.  If it was taken Wednesday when McCain was in Manchester (or the day after), that would be a reason for the race to (perhaps temporarily) tighten - McCain visited the state.  Obama didn't.

[Eraserhead]

NH is slightly concerning.

[Lunar]

I think "regression to the mean" would be a better word than "tightening"

If one poll overstates Obama's lead then the next one is extremely likely to show "tightening" regardless of whether the race has actually changed.

[classical liberal]

I think "regression to the mean" would be a better word than "tightening"

If one poll overstates Obama's lead then the next one is extremely likely to show "tightening" regardless of whether the race has actually changed.

What's with the strikethrough?

[classical liberal]

Okay, what I should have said was that more than likely it's not statistical noise. Better?

I guess.  Honestly I don't know at what point something becomes less likely to be statistical noise.  The 50% confidence interval, I guess?  Not sure when that's reached.  Wish there were a calculator for that.

I was just pointing out being concretely sure it isn't statistical noise when it's within the 95th confidence interval is a bit dangerous.  Methodology/sampling errors + statistical noise = a lot of uncertainty, maybe 1-in-7 polls or something like that.  But, yeah, better, def.

If we assume a normal distribution, then the reported MoE for a 95% confidence is stdev*1.96, whereas the MoE for a 50% confidence is stdev*0.675.  That means a move of (MoE=4%)*.675/1.96=1.38% is more likely than not to be non-noise legitimate movement.  Of course, that is for sampling error.  There is also systematic error, such as the wording of questions (I still can't get over the fact that most pollsters ask how you feel about George Bush immediately before asking about the presidential race).

In any case, since McCain just visited that tiny empty state, the echo chamber of local press can be expected to have given him a transient bump that a good pollster should be able to detect while it is still fresh.

[Alcon]

Thanks, RWN! 

[cinyc]

The New Hampshire poll was taken yesterday:

This telephone survey of 700 Likely Voters was conducted by Rasmussen Reports on October 23, 2008. The margin of sampling error for the survey is +/- 4 percentage points with a 95% level of confidence.

[Lunar]

I think "regression to the mean" would be a better word than "tightening"

If one poll overstates Obama's lead then the next one is extremely likely to show "tightening" regardless of whether the race has actually changed.

What's with the strikethrough?

I was trying to do word(s)

[Lief 🗽]

Rasmussen's polls don't really make a ton of sense when compared to the national +7 Obama is getting, but whatever. These numbers are good enough.

[Rowan]

NH
R’s 90% McCain- 10% Obama
D’s 91% Obama- 5% McCain
I’s 51% Obama- 42% McCain

IA
R’s 95% McCain- 1% Obama
D’s 91% Obama- 7% McCain
I’s 46% Obama- 44% McCain