Rasmussen Tracking Poll [Obama vs McCain]

[CARLHAYDEN]

45% (+1) trust McCain most when it comes to economic issues and managing the economy while 42% (+2) prefer Obama.

On national security issues such as the War in Iraq and the War on Terrorism, 49% (-2) have more trust in McCain while 41% (+4) prefer Obama.

Then what the heck are they voting on?

Well, let me give you one example (from the ABC/WaPo/TNS poll)

"Regardless of who you may support, who do you trust more to handle immigration issues: Obama or McCain?" Candidate names rotated
 
                      McCain Obama Both (vol.) Neither (vol.) Unsure
                         %          %       %               %                   %
  
5/8-11/08        37         42        3               10                    7

[CARLHAYDEN]

Alaska is going to be within a few points (3 at most, 1 at least, if what I'm hearing is correct - probably McCain +2)

4 to be correct.

Where are you seeing that?  Is the poll out?  I thought the extrapolation was 43-41.

Ah, Alcon, I don't quite know how to tell you this (you do seem to have trouble understanding basic concepts), but, extrapolating on survey results is stongly frowned upon in the survey research industry.

[CARLHAYDEN]

Alaska is going to be within a few points (3 at most, 1 at least, if what I'm hearing is correct - probably McCain +2)

4 to be correct.

Where if Vorlon when we need him!?!

I am posting this reply merely to prevent your deleting you assertion that extrapolation is not frowned upon in the survey research industry.

Where are you seeing that?  Is the poll out?  I thought the extrapolation was 43-41.

Ah, Alcon, I don't quite know how to tell you this (you do seem to have trouble understanding basic concepts), but, extrapolating on survey results is stongly frowned upon in the survey research industry.

Extrapolating cross-tabs from the same survey, however, is not frowned upon.  I just managed to forget about the Undecided sample, which evidently broke for McCain

[CARLHAYDEN]

It's not extrapolation; I was using the wrong phrase.  It's using sub-samples to calculate other samples.

CARL, this is essentially what I did.  Here's an example:

Male (51%): Obama 51%, McCain 48%
Female (49%): Obama 54%, McCain 45%

Now, 51% of the sample is male and 49% is female.

Thus, the Obama sample is (0.51*0.51)+(0.49*0.54) = 0.5247 = 52% Obama

And the McCain sample is (0.51*0.48)+(0.49*0.45) = 47% McCain

I realize this introduces some rounding error, but when the sub-sample is from the same poll, it does give you a very close approximation of the results -- unless you screw up the math by forgetting Undecideds, which I did.  This should work in any instance where you have samples that constitute the entirety of the poll, and then results for what you're trying to determine for those samples.

You can feel free to tell me where I'm wrong on the math, but I do not believe I am.    And I haven't ever deleted a post and claimed I didn't make it, so you're really just archiving your inability to use the QUOTE tag.

Alcon,

First, extrapolation for "undecideds" according to the proportion of "decideds" is very, very wrong!

It assumes that the "undecideds" are reflective of the decideds (generally false).  The undecideds are generally those with lower SES than the decideds.  Also, the undecideds several months prior to an election are not only different from the decideds at that time, but they also differ from the undecideds in the closing days prior to an election.

It also runs counter to experience.  You may have heard that the general rule is that when there is an incumbent involved in a race that is essentially even among the decideds, the undecideds will generally support the challenger.

Further, what you are attempting to do is statistically invalid.  While the MoE for a total poll may be x.  If you try to extrapolate based on subsamples, you drastically increase your MoE.

[CARLHAYDEN]

Where do you get the idea that a subsample of a survey has the same MoE as the total sample?

This is why some polls interested in a particular group use an oversample so that they can get some statistically valid data from the subsample.

You really need to take a course in survey research.

[CARLHAYDEN]

Using fake numbers and arbitrary assumptions, Alcon gets the results he wants.

While doing your abracadra routine, you still have NOT dealt with the problem of allocating the undecideds.

You are merely assuming that they will vote the same way that the decideds are voting, weighted for one demographic!

If you delve into (admittedly delayed) information from the University of Michigan Survey Research Center (they've been at it for sixty years), you will find that undecideds are a completely different type than the decideds.

[CARLHAYDEN]

Using fake numbers and arbitrary assumptions, Alcon gets the results he wants.

While doing your abracadra routine, you still have NOT dealt with the problem of allocating the undecideds.

You are merely assuming that they will vote the same way that the decideds are voting, weighted for one demographic!

If you delve into (admittedly delayed) information from the University of Michigan Survey Research Center (they've been at it for sixty years), you will find that undecideds are a completely different type than the decideds.

Carl,

since you misunderstood what Alcon said you could still save some face by acknowledging that. The undecideds in this case are not undecideds in the presidential race but undecideds in the senatorial race. Those undecideds may have a preference in the presidential race. Alcon forgot to include those in his calculation. The term extrapolation was a mistake on his part (as he noted) since that is not what he did. He merely used the subsamples presented by Rasmussen Reports (which add up to the total sample) to calculate the result for the whole sample. This is commonly done by most of us whenever a poll releases results from a set of subsamples that add up to the whole sample before they release the topline numbers. There is nothing statistically unsound here, since there are no new assumptions introduced.

First, I realize that you and Alcon does some funny things with numbers to get the results you want, but that does not make such practices valid or sound.

What Alcon did was to assume that if adjusted for one demographic factor (gender) he could project the undecided vote based on the decided vote.

Now, let me give you an example of how practicing this voodoo analysis results in weird results.

In 2004 there was a site online (can't remember the name) which sought to project the results in the states based on the national demographic preferences for the candidates.

Given this method, it had Minnesota supporting Bush and Mississippi supporting Kerry!!!  After all, a clear majority of whites nationwide preferred Bush, and an overwhelming majority of Blacks nationwide favored Kerry, and needless to say the percentage of the black vote in Minnesota is very small, and in Mississippi, far larger than the national average.

If we were to have a large enough sample (of the undecideds and the decideds) I believe you will find that while the gender distribution will be only slightly different (due to central tendency), the SES, particularly educational attainment and income will be dramatically different.  I also suspect that in this (2004 Presidential) election, the age distribution will be significantly different.

So, merely adjusting for one demographic does NOT adjust for others!!!

Second, there are other problems as well.

Undecideds have a different outlook on politics than decideds.  Again, check UM SRC data.  They tend to vote more against, than for (which explains why incumbents do so bad with them).

In conclusion, just assuming that based on one demographic componet, undecideds can be allocated in a particular fashion is foolish as well as unsound and invalid.

[CARLHAYDEN]

Using fake numbers and arbitrary assumptions, Alcon gets the results he wants.

While doing your abracadra routine, you still have NOT dealt with the problem of allocating the undecideds.

You are merely assuming that they will vote the same way that the decideds are voting, weighted for one demographic!

If you delve into (admittedly delayed) information from the University of Michigan Survey Research Center (they've been at it for sixty years), you will find that undecideds are a completely different type than the decideds.

Carl,

since you misunderstood what Alcon said you could still save some face by acknowledging that. The undecideds in this case are not undecideds in the presidential race but undecideds in the senatorial race. Those undecideds may have a preference in the presidential race. Alcon forgot to include those in his calculation. The term extrapolation was a mistake on his part (as he noted) since that is not what he did. He merely used the subsamples presented by Rasmussen Reports (which add up to the total sample) to calculate the result for the whole sample. This is commonly done by most of us whenever a poll releases results from a set of subsamples that add up to the whole sample before they release the topline numbers. There is nothing statistically unsound here, since there are no new assumptions introduced.

First, I realize that you and Alcon does some funny things with numbers to get the results you want, but that does not make such practices valid or sound.

What Alcon did was to assume that if adjusted for one demographic factor (gender) he could project the undecided vote based on the decided vote.

No, that was not what Alcon did. I have bolded the part in my post where I explain what he did. Let's say you have a poll which says how Texas whites are going to vote and how Texas blacks are going to vote and how Texas Hispanics are going to vote. If we assume that there are no other ethnic groups in Texas we could then calculate the overall standing between the two candidates based on their standings within these subsamples. If one did this but forgot to include Hispanics, looking only at blacks and whites, the result would however be wrong. And that is what Alcon did in this case.

Now, I would like to remind you that I have never used name-calling or gone out of my way to attack you and I would prefer that you didn't insinuate things such as me doing "funny things" with numbers. I don't and neither did Alcon in this case.

First, I never mentioned Texas in this thread, that's just another allegation you made up.

Second, the point of this thread (which you appear to have missed) is that you cannot appropriately allocate undecideds.

Alcon attempted (improperly) to allocate the undecideds.

[CARLHAYDEN]

Alcon attempted (improperly) to allocate the undecideds.

How many times do I have to explain that I didn't allocate Presidential undecideds?  Here, let me try one more time:

I didn't allocate Presidential undecideds.

I allocated people who were undecided in the Senate race, but were decided in the Presidential race.  I allocated decided voters who were undecided in another race BUT decided in the presidential.  You can't possibly be this slow in understanding.  Read this time.

Here is one last example.  Again, theoretical numbers.  On the left is the respondent's opinion in the Senate race; on the right, Presidential.

Stevens (50%): McCain 85%, Obama 11%, Undecided 4%
Begich (45%): Obama 86%, McCain 9%, Undecided 5%
Undecided (5%): Obama 40%, McCain 36%, Undecided 24%

Here's a graphical representation:



So, 5% of voters are undecided in the Senate race.  We can't allocate those for the Senate race, but we can allocate those who are decided in the Presidential.

- 40% of Senate undecideds are decided for Obama.  40% of 5% means 2.0% of the overall sample are "undecided Senate voters decided for Obama."

- 36% of Senate undecideds are decided for McCain.  35% of 5% means 1.8% of the overall sample are "undecided Senate voters decided for McCain."

- 24% of Senate undecideds are undecided Presidentially, too.  24% of 5% means 1.2% of the overall sample are "undecided Senate voters undecided in the Presidential race."

You can see the contribution of Undecided Senate voters to the Presidential options Decided McCain, Decided Obama, and Undecided, below:



You can also see the results of performing the same operation with Decided Stevens and Decided Begich, and then adding to estimate the percentage for the Presidential response (with rounding error) for the overall sample.

So, tell us where I am attributing voters who are Undecided in any race as being Decided in that race, as you claim I am.

Well, now that we're no longer dealing with "fake" numbers, lets look at your "assumptions."

You assume that seventy six per cent of the persons listed as undecided in the Presidential preference question were in fact lying, and that by projecting from results from demographics of the Senate questions onto the Presidential question you can get the results you want.

It doesn't work that way!!!

[CARLHAYDEN]

Well, now that we're no longer dealing with "fake" numbers

Actually, no, this is the same concept that I've been trying to explain the entire time that you seem incapable of understanding.  The fact that you think this is a new concept shows that you have been confused this entire time but hurling accusations anyway.

You assume that seventy six per cent of the persons listed as undecided in the Presidential preference question were in fact lying, and that by projecting from results from demographics of the Senate questions onto the Presidential question you can get the results you want.

It doesn't work that way!!!

No.  In those theoretical numbers, 76% of Senate undecideds were decided in the Presidential race, and I allocated those to the Presidential race.  They were NOT undecided voters in the Presidential race.

There's nothing that stops someone from being undecided in the Senate race and decided in the Presidential.  If 25% of voters are undecided in the Senate race, but none of those undecided Senate voters are undecided in the Presidential, you're arguing that 25% would still be undecided in the Presidential.  Obviously, that makes no sense and a few seconds of thought should have told you that.

Seriously though, if you are having this much trouble understanding a relatively simple concept, please do contact the Vorlon.  Maybe he can make you understand.

I don't think you are incapable of understanding, but simply that you do NOT want to understand.

First, NOTHING you have done validly indicates the breakdown of the undecided voters in the Presidential contest.

You seem to have obliquely acknowledged that extrapolation is invalid (which was your initial contention).

Are you still contending that on ONE demographic factor you can project the breakout of the undecideds in the Presidential race?

Finally, are you contending that the breakout in a poll (not results) in another race by party of candidate has a clear correlation to the breakout of the results in a Presidential poll?

Or are you now simply acknowledging what I said from the beginning, that there is currently no valid way of determining the eventual vote of the undecideds in a Presidential race?

[CARLHAYDEN]

Scattered across this thread is an ongoing discussion about an effort Alcon made to project the poll results in Alaska from a national poll.

In post #115 on this thread, Alcon opined “Alaska is going to be within a few points (e at most, 1 at least)

In post #118, Mark Warner corrected him by noting that the actual margin was “4 to be correct.”

So farm Alcon’s opining was merely wrong, but it got worse. 

In post #119 stated “I though the extrapolation of 43-41.”

In post #120, I advised Alcon that “extrapolating on survey results is strongly frowned upon in the survey research industry.”

Now, Alcon gets really dishonest.

In post #121 he asserts that “Extrapolating cross-tabs from the same survey is not frowned upon.”

Remember, in his post #119, Alcon stated, when being advised by Mark Warner of the actual results stated “Where are you seeing that?  Is the poll out?”

So, he was NOT “extrapolating cross-tabs from the same survey”!  At the time Alcon made his guesstimate, he was unaware of the Alaska survey!

Finally, in post #124, Alcon states: “Its not extrapolation.  I was using the wrong phrase.”

Further, in Post #124 Alcon states that what he was taking the preferences by one demographic (gender) in one poll (the national Rasmussen) and projecting it (my term) onto Alaska, while making the minimal adjustment for the slightly greater male component in the Alaska electorate than in the national electorate.

However, in post #132, I tried to advise Alcon (and the thoroughly confused Gustaf) that you cannot validly project a state result from a national result using just one demographic component)!

In post #126 Alcon further notes that “I accidently ignored the break-out of the Undecids.”

However, in the examples which he provided, using “fake” numbers (his term) and arbitrary “assumptions.” (post 126).did allocate undecideds!

Now, there were three basic concepts that were argued in the discussion:

First, the invalidity of “extrapolation,” which Alcon subsequently seems to have acknowledged was invalid.

Second, there is no valid way to allocate undecideds.  Alcon seems to have acknowledged this point.

Third, one cannot validly project from one poll to another the results based on one demographic component.  Anyone who thinks Alcon’s approach is valid should try projecting national results on the District of Columbia using gender, as Alcon did for Alaska!  LOL

The rest of Alcon’s diatribe was mere smoke-screen to try to obscure these points

[CARLHAYDEN]

Yet again, you've completely failed to understand what's going on, CARL.

Rasmussen released the Senate side of a Senate/Presidential poll, with cross-tabs that indicated Presidential support by Senate support.  Using the method I described above, these results correctly predicted McCain +4.  I made the mistake of not including the Presidential preferences of voters undecided in the Senate race, which incorrectly came out to McCain +1-3 (with rounding error leeway).  My conceptual methodology was fine; I just made an arithmetic error.

Calling this an "extrapolation" was incorrect, since it implies I was "assuming" something based on trends or arbitrary allocations.  I was just extracting results that already existed in the poll.

As for:

You must be logged in to read this quote.

Where did this BS come from?  I've never said that.  I was using gender as an example of what I'll call a "full-sample subsample set" (FSSS)*, and I haven't even mentioned the Rasmussen national poll.

I really do encourage you to contact the Vorlon, Sam Spade, or any other poll-savvy poster (or one with remotely competent math knowledge), to explain to you that there's nothing wrong with what I did.  The only source of non-human error would be rounding error.

* - Something like male + female, or Begich + Stevens + Undecided, that adds up to 100% of the sample.

First, my apologies on one respect, i.e. I have never seen a pollster release the Senate side of a poll prior to the Presidential side.

It appeared to me that you were projecting from the existing national poll.  Your use of fake numbers and assumptions made what you are now asserting very unclear.

Second, there is still a minor problem, i.e. the hidden assumption that those voting in the Presidential election are the same as those voting in the Senate election.

While the "roll-off" typically is modest (1 to 2%), it can be substantial (watch what happens in Montana this year).

[CARLHAYDEN]

Friday - July 18, 2008:

Obama - 47% (+1)
McCain - 46% (nc)

There has been much discussion about the potential demographic changes brought about by Obama’s historic candidacy and the fact that he won the nomination by ending Hillary Clinton’s historic candidacy. Rasmussen Reports reviewed data from our July polling and found somewhat surprisingly that Obama’s support looks a lot like John Kerry’s. The only big difference is that Obama is currently doing about five points better against McCain than Kerry did against George W. Bush.

Four years ago, exit polls showed Bush defeating Kerry among white men by a 62% to 37% margin. Today, Obama is doing four points better than that and trails 58% to 37% among white men.

The tale is the same among white women. Bush won that demographic by eleven percentage points, 55% to 44%. Obama is doing five points better and trails by only six, 48% to 42%.

Among non-white females, Obama leads by fifty-four points, up three from Kerry’s margin of fifty-one points. However, Obama lags a bit among non-white males. This year’s presumptive nominee leads by twenty-nine points among that group, down from Kerry’s thirty-seven point margin.

Take the number of "non-white males" in the sample, get the square root, multiply that by 0.98, then divide by the total number of "non-white males" in the sample, and you'll get the MoE.

I would estimate that the MoE is probably be at least seven per cent, and perhaps as high a sixteen per cent, depending upon subsample size.

[CARLHAYDEN]

What´s even more interesting: I don´t get how Obama is ahead by only 1% overall, if he´s getting 44% of the white vote, to McCain's 50%. Kerry got 41%, Bush 59%. Obama's getting higher shares among African-Americans and Hispanics. Is Rasmussen's sample 90% White ? Because on Election Day it will be 73-75% ...

That's a good point.  If the sample is 25% non-white, Obama would have to be leading by a barely 3:2 margin among non-whites.  Kerry's margin was more like 5:2, even in the ill-adjusted exit poll.

It´s really freaking me out, after running through his numbers on the calculator:

Let´s assume a very pessimistic sample for Obama:

80% Whites: Obama @ 44% support
9% African Americans: Obama @ 92% support

With these numbers alone, Obama receives a minimum of 43.5%.

9% Hispanics
2% Others

To get 47% overall, he would have to get only 1/3 (!!!) of Hispanics and Asians. Last time I checked, Obama got more than 60% in every poll (Rasmussen and Gallup) ...

Let me suggest a slightly different breakdown by race/ethnicity:

Race/ethnicity                    % of Voters                    Percentage for Obama                    % of Voters

White (nonhispanic)               76                                         41                                             31.16

Black (nonhispanic)                12                                         95                                             11.40

Hispanic (all races)                   8                                         67                                               5.36

Asian (nonhispanic)                  2                                         56                                               1.12

All others (nonhispanic)            2                                         56                                               1.12

Total                                     100                                                              50.16

[CARLHAYDEN]

Let me repeat a point I made a few days ago.

Rasmussen is improperly pushing leaners, who really aren't leaners.

So, Obama does NOT have the support of 44 % of whites and McCain does NOT have the support of 50 % of whites.

[CARLHAYDEN]

I'd expect Obama to get a bump in the polls due to the hurricane coverage. Every time Obama is out of the spotlight his numbers rise.

like...during the DNC?

His best poll numbers existed when he was on vacation in Hawaii.

A very perceptive observation.

Most people don't want Obama, they just don't want Bush.

If the focus is on Obama, even with the fawning media, he may well lose.

If the focus is on Bush, then Obama will probably win.