According to Gallup, Romney Should Win

Like a lot of folks, I follow opinion polls.  Unlike a lot of people, I remember what I learned in my Statistics classes.  This means that I try not to make the most common mistakes which happen when folks read and discuss polls.   I have examined historical trends and the relevant vectors of this election in theGalluppoll, and find significant evidence that the Republicans’ ticket of Romney & Ryan will defeat the Democrats’ ticket of Obama & Biden.

 

First, some points about the polls.  Political opinion polls are useful indicators of the public mood, but there are a number of common errors in their consideration.  One of the most common mistakes is aggregation; Aggregation is a mistake because different polls use different methodologies, often slight in variation but distinct in effect.  One poll may consult ‘Likely Voters’ while another asks ‘Registered Voters’ (while another may just ask ‘Adults’ and different polls may have different standards for determining who is a ‘Likely Voter’), polls differ in weighting demographic samples, party affiliation, and other significant vectors.  Statistics is only valid if consistent methods  are used, and aggregating results from different polls invalidates conclusions by mixing methods.  A way to understand this would be if a patient needs to lose weight.  He weighs himself on his home scale and it reads 240 pounds.  At his doctor’s office, however, the scale reads 243 pounds.  If you believe the doctor’s scale is more accurate than his home scale that’s fine, but let’s say the same patient exercises a bit more and watches his diet a little better.  If his home scale tells him he now weighs 235, while we may expect the doctor’s scale to be different we would expect to see the same amount of weight loss on that scale.  Similarly, a more effective way to read opinion polls is not to compare Poll A to Poll B, but to note trends in each poll over time, or look at one poll in detail, considering historical behavior as well as current statements.  In other words, a political opinion poll should be considered valid if that poll uses reasonable and consistent methodology, shows how it reaches its results, and is willing to report its history against actual election results.

 

At this time, the only national opinion poll which meets all three conditions at a high level of veracity is the Gallup Organization.  Other polls may well use consistent methodology, but most will only publish detailed demographics for ‘premium’ customers, and few have even been in business for more than a decade, let alone since the FDR Administration.  What’s more, the Gallup people quite openly publish their track record, mistakes and goofs along with their successes, which is not only unique but generates strong credibility for Gallup.  Frankly, I’ve been watching and evaluating polls since 2000 in as much detail as I can, and no one else comes close toGallupfor reliability.  So, for this essay I am considering the available information fromGallup.

 

So, let’s start with today’s numbers.  The good news for President Obama is thatGallupshows him with a 1 point lead over Governor Romney, 47% to 46%.

 

http://www.gallup.com/home.aspx

 

But President Obama’s Job Approval is down to 43%.  That number is a big problem for Obama, so let’s start there. Galluplists the historical track record of Presidential Job Approval, and this can be compared to election results.

 

http://www.gallup.com/poll/124922/presidential-approval-center.aspx

 

There have been sixteen Presidential elections since World War 2, of which ten featured a sitting President on the ticket.  Gallup’s record shows that no Job Approval poll was taken for Truman between July and October of 1948, so that limits us to consider the nine remaining elections:

 

1956:  Labor Day Approval 68%, Election 57.8% (-10.2%);

1964*:  Labor Day Approval 74%, Election 61.3%  (-12.7%);

1972:  Labor Day Approval 56%, Election 61.8% (+5.8%);

1976:  Labor Day Approval 45%, Election 48.1% (+3.1%);

1980*:  Labor Day Approval 32%, Election 41.0% (+9.0%);

1984:  Labor Day Approval 54%, Election 59.2% (+5.2%);

1992:  Labor Day Approval 39%, Election 37.7% (-1.3%);

1996*:  Labor Day Approval 60%, Election 49.2% (-10.8%);

2004: Labor Day Approval 49%, Election 50.7% (+1.7%)

 

(* Democrat incumbent)

 

Of those nine elections, the incumbent had a 1.1% loss between his Labor Day Job Approval and the Election Results (indicating Obama could finish with just 41.9% of the Popular Vote), but in the three elections with a Democrat President and a Labor Day Job Approval rating, the incumbent lost 4.8% between the Job Approval and the Election Results.  If that last trends holds true this year, President Obama may finish with less than forty percent of the Popular Vote.  The reason I do not think this likely, is because only three elections are on record with a Democrat Incumbent, too few to establish a reliable statistical sample.  Nonetheless, President Obama’s poor Job Approval as of today is a bad sign for his election results.

 

Gallupalso publishes the poll results for the Presidential elections it has covered.  In these elections, the September 1 poll results may be compared to the actual election results, as a means to determine how accurate those polls are in predicting outcome and the resolution of undecided voters.  The record of polls from the relevant elections can be found here:

 

gallup.com/poll/9442/gallup-presidential-election-trialheat-trends-19362004.aspx

 

There are fifteen Presidential elections after the World War 2, for which a late August or early September poll was taken which could be said to represent the Labor Day sentiment.  Of those fifteen polls, the Democrat candidate gained an average 1.6% from September to the election, while the Republican candidate gained an average 4.2%.  Matched toGallup’s present polling, this would project a 50.2% to 48.6% Romney victory.

 

When only elections with a Democrat incumbent are considered, the change from Labor Day polling to the election is a 0.5% loss for the Democrat, and a 7.7% gain for the Republican challenger.  Clearly, is accurate this trend would project a decisive win for Romney.

 

All of this may seem tenuous, but for two salient factors still to be considered.

 

First, all elections depend in large part on the enthusiasm of the party base.  It’s no wild guess to expect that Republicans will vote for Romney, or that Democrats will vote for Obama.  The questions, then, come down to how independents will vote, and how many Republicans and Democrats show up at the polls.  In 2008, strong Democrat enthusiasm for Obama coupled with lukewarm Republican support for McCain, created a clear Democrat advantage at the polls, which produced a clear majority in the election.  In 2004, both parties showed strong energy which kept the election close;Gallup’s final poll in 2004 showed a 49-49 tie.   With this in mind, consider the following article fromGallup:

 

http://www.gallup.com/poll/156524/Voter-Engagement-Down-Slightly-Last-Two-Elections.aspx

 

The article shows a lead for Republican energy over the Democrats, especially when asking who is following the election “very closely”.

 

Next, consider the question of the undecided voters.  Gallup’s poll reflects a seven percent undecided portion, a number not only well beyond both the statistical margin of error and the margin between the two candidates, but consistent with most presidential elections at this point in the election.  Of the nine elections with a sitting President as candidate, six had undecided numbers between six and seven percent.  It is an important consideration, then, to see what happened with those voters.  Over the six elections with comparable undecided portions, the Republican took fifteen times as many voters as the Democrat (an average gain of 3.0% against a Democrat gain of 0.2%).  When all nine are considered, the advantage grows to a Republican average gain 4.5%, versus a Democrat gain of 0.3%.  Again, this favors Romney in this election.

 

But why should Romney claim more of the undecided voters than Obama?  The answer comes from the three kinds of efforts a candidate must make in an election.  A candidate for President must do three things, ignoring none of them:

 

  1. Build his brand
  2. Defend his brand against his opponent’s attacks
  3. Attack his opponent’s brand

 

 

To see how this plays out, consider 2004 and 2008.  In 2004, Bush was able to run on his record, while Kerry had to establish his identity for voters.  This gave Bush an initial advantage he was able to ride to re-election.  In 2008, however, neither Obama nor McCain had an executive record on which to run, so the decision came down to creating an attractive identity, where Obama’s eloquence made the difference.  This year, Obama will be judged on his record, against Romney’s image as a potential successor.  As noted before, most Democrats and Republicans will have already decided to back their party’s candidate, leaving only a few Democrats and Republicans, along with the Independents,  to hand out the remaining votes.  Obama has enjoyed support above 48% only once, and has spent most of the General Election locked in at 47%.  Frankly, the only way Obama can significantly increase his numbers would be for Romney to commit some blunder that seriously damaged his numbers and led to voters making late choice changes.  This is what happened in 2008, when Sarah Palin’s misstatements created doubts about McCain’s judgment, resulting in nearly a ten-point loss of support in a couple weeks, with Obama the happy beneficiary.  The problem for Obama this year, is two-fold:  First, Obama’s camp has to deal with mis-statements by both the President and his vice-president. Second, Romney’s choice of Ryan created an issues-focused team that may not be the most exciting in memory, but which is going to be focused and clear.  In short, the voters know all about Obama and Biden, but some are still learning about Romney and Ryan, creating opportunity to the Republicans to gain support beyond what they have now.  At this time, the numbers suggest Romney is in a much stronger strategic position.

 


 

Bill Clinton to Ted Kennedy: In The Past, Obama Would Be 'Carrying our Bags'
But he's so likeable
  • http://www.facebook.com/people/Adam-Smith/100000513036601 Adam Smith

    Since you’re “good at statistics” may I suggest you look at the likely electoral vote count.

    Tells a very different story.

    And since it’s the electoral college and not the popular vote that matters, you’re missing the big picture.

    • http://opinion.ak4mc.us/ Scribe of Slog (McGehee)

      Link, please?

      • JWH

        Here’s one link:

        http://www.realclearpolitics.com/epolls/2012/president/2012_elections_electoral_college_map.html

        I think this is something that updates over time (and I don’t have a way to screenshot it), so I’ll encapsulate what it looks like:

        As of Sept. 4, 2012, RCP lists the following:

        Obama-Biden
        Solid Obama: 142 electoral votes
        Likely Obama: 30 electoral votes
        Leans Obama: 49 electoral votes
        ——————————————
        Total: 221

        Romney-Ryan
        Solid Romney: 76 electoral votes
        Likely Romney: 58 electoral votes
        Leans Romney: 57 electoral votes
        ——————————————-
        Total: 191

        RCP also lists 126 votes as toss-ups.

        Switch to RCP’s “no-tossups” map, and you have Obama at 332 electoral votes to Romney’s 206.

        ====================================

        Despite the down economy, President Obama has an advantage right now.

        • http://opinion.ak4mc.us/ Scribe of Slog (McGehee)

          What metric are they using to determine vote outcomes in the various states? Everything I’ve seen shows that Obama (1) can’t expect to gain any states that went to McCain, and (2) stands to lose several that he won last time.

          RCP has got to be applying anomalous 2008 party ID to a post-2010 landscape, which makes no sense at all.

          • JWH

            I think their metric is some sort of averaging of the polls in each state as they are released.

          • http://opinion.ak4mc.us/ Scribe of Slog (McGehee)

            In which case the party ID weighting in most polls will prove problematic. If the polling organizations start taking note of the actual party ID findings that have been coming out recently you’re going to see some big shifts on that EV map.

          • JWH

            Hmmm … are they using party ID, or are they using “will you vote for Romney vs. Obama?” Those are two very different questions.

          • http://wizbangblog.com/author/rodney-graves/ Rodney G. Graves

            “Do you consider yourself to be a Democrat or a Republican?”

            Was +7 D in 2008, is currently +4 R (an 11 point swing).

          • JWH

            Interesting. Though if this election comes down to hanging chads again, I’m moving to Canadia.

          • 914

            Is that by rodondo beach or is that a swing state?

          • http://opinion.ak4mc.us/ Scribe of Slog (McGehee)

            And then there’s this. Hard to imagine that translating into an EV victory for Obama.

          • Guest

            I think they take an average of the most recent polls in each state.

    • retired.military

      Obama will be lucky to get 200 electoral votes.

      • 914

        If the populace were even half as smart as your average dimwitocrat, Barry would not get 20..

      • http://pulse.yahoo.com/_IZ5BM5GNLA54OADSWGSXAMA7SY Jay

        RM… Are you looking at the same maps as the rest of the country? It’s a clear lead for Obama with well close to 250 over Romney’s 170.

        • Dana

          Jay: Are you taking into consideration that the swing states are bending toward Romney at this point? Didn’t think so. Also, Obama has lost IN, and looks like he will lose some other states that went for him in ’08. You are obviously going by the 2008 electoral map and taking it for granted that Obama states in 2008 will be the same this time, and data points a different direction. Look into several different maps, and click on the interactive ones to see what their individual results are now. You will be amazed.

    • 914

      Yep, the big picture is 16% unemployment and gas and food prices through the roof! Say goodbye to your hero!

    • PBunyan

      Aparently Adam & JWH missed the part in the post where DJ was talking about scales. RCP is an average with trash thrown in. It can be nothing more than trash.
      It’s like if you take a glass of wine and pour it into a barrel of sewage, the wine becomes sewage; if you take a glass of sewage and pour it into a vat of wine, the wine becomes sewage.

  • Par4Course

    Mr. Smith makes a valid point. Presidential elections are based on the electoral vote, not the popular vote Remember 2000: AlGore won the popular vote but G.W. Bush won the election. (BTW, AlGore is now trying to abolish the electoral college.)

    If a candidate had the support of 51% of the voting public, he would win if his voters were spread proportionally throughout the 50 states. But that’s never the case. Obama will win by a wide margin in the dark Blue states, and Romney will win big in the bright Red states. It therefore comes down to the voters in the swing states, those that are not overwhelmingly Blue or Red. Further, it really comes down to the independent or swing voters in the swing states – those folks who could vote D or R, depending on how they’re feeling on November 6.

    I’ll put more stock in the polls when we get close to Election Day. We’re still about 64 days away, and a lot can happen in that two-month period.

    • mrisinger

      Not that I disagree with your general point about swing states, it is still the undecided voters that determine those states, and the behavior of those voters in general is what this article is trying to predict.

    • http://opinion.ak4mc.us/ Scribe of Slog (McGehee)

      Remember 2000: AlGore won the popular vote

      That’s been asserted often over the last 12 years — yet if all 50 states’ totals had been as closely examined as Florida’s, how accurate would it prove to be?

      • http://www.rustedsky.net JLawson

        Depends on how many military absentee ballots would have to be disqualified, I think. That still pisses me off 12 years later…

    • djdrummond

      OK, let’s talk about the states. When you look at what I wrote about polls’ reliability (consistency, history, transparency), you should note that the state polls are nowhere near the Gallup standard. That’s not to knock the state polls, but they are both relatively new, and they lack transparency about how well they have done in the past.

      Next, don’t forget that you cannot aggregate the state polls to determine their message; you have to choose one poll and follow it for trends, but compared to the national polls, that is a slow and cumbersome process.

      Also, pay attention to how large the undecided portion of the state polls is of the whole. Many of the state polls show a leader BELOW 50 percent, meaning it’s not locked away. Also, since state polls have a much smaller respondent pool than national polls, they have a much large statistical margin of error. I will save you the time; right now less than half of the states are anything like decided.

      Which brings us back to the national poll. It is true that the election is decided by electoral votes from the states, but the national results are tied to the states in total; it is impossible to perform poorly in one but control the other. Only in outlier years like 1968 or 2000 is it possible to have a plurality in the popular vote but lose the electoral vote; if a candidate wins the popular vote by a clear majority, as Gallup’s trends indicate will happen for Romney, the EV will also produce a Romney win.

      • JWH

        DJ … did you take a look at the RCP map?

        • http://opinion.ak4mc.us/ Scribe of Slog (McGehee)

          Unless the RCP map is based solely on Gallup polls, your question isn’t on point.

  • Paul Hooson

    Most of your points are dead-on here, DJ. However, Scott Elliot over at Election Projection, who has always had the most accurate election prediction analysis of any site has an interesting finding for his Saturday weekly analysis. He has Romney winning the popular vote, but losing the electoral college by a 303 to 235 margin, or 68 more electoral votes than Obama needs to win. Further, the Democrats have their convention this week, giving the president, if successful one more good shot to blunt any slight bounce that Romney received last week.
    I was actually a huge fan of the elder Romney, George Romney, but he seemed to have problems getting elected president, running two failed campaigns, and finally working as the Housing secretary under President Nixon(whom I also worked for when I was just 17). But, the son, Mitt, is on on his second try to run for president as well, and just doesn’t quite seem to have closed the deal with many voters despite the very disappointing Obama record. Obama may have had 2.9 million jobs created during his administration, but that is far less than really hoped for when you consider population increase. Further, only something over 500,000 of those jobs went to women. And unemployment among African American women actually increased. Romney claimed that he would add 12 million jobs in his RNC speech, but he failed to really state just how exactly that would happen. And Ryan might actually be a slight drag on the ticket as well, admitted lying about his marathon running time performance, misleading voters about the GM plant story, etc. only writing and passing just two pieces of legislation in his 14 years in Congress, despite drawing a salary of $174,000 a year plus other benefits for staff, etc. for 14 years. Congress only has about a 10% approval rating with voters right now, and the performance of guys like Ryan is part of this voter frustration equation. Choosing any member of Congress is probably more or a drag than a benefit to the Republican ticket right now. although Joe Biden certainly has his own goofy moments which are a drag to Obama as well, Often Obama is like the straight man to Biden’s stooge act.
    Romney has one more last good shot to close the deal with the voters by posting strong debate performances. But, he continues to offer up unrealistic views on foreign policy, that aren’t based off the real world, as well as weak specifics on job creation, etc. Most of his economics are for the most part warmed-over Bush era economics, even if some ideas like tax cuts to business might spur some new job growth. Yet, the truth is that life will probably get worse under either Obama or Romney before it gets better, as gas prices will only continue to rise, and the drought will only raise food prices significantly in the coming months. And a new recession may be lurking for late 2012, early 2013.
    As a challenger, Romney likely has a little hidden lead right now, probably by about 3 points or so. Yet, it appears that Obama is leading in Ohio. And guess what? Ohio always votes for the winning candidate. Tell me who wins Ohio, and I’ll tell you who wins the election. It all comes down to just this one state. If Obama wins Ohio, he wins the election. If Romney wins Ohio, then it’s all over for President Obama.

    • 914

      Ohio will go ABO 50% – 45% This election was never in doubt! Landslide 101 Live with it!! lol

  • http://www.wizbangblog.com David Robertson

    The only poll that counts is the one that takes place in voting booths.

  • Commander_Chico_Cognoscente

    Call me one week after the Israelis bomb Iran, about the end of this month.

    • 914

      Ok, Nostadumus I will..

      sorry for the typo.. meant nostadumass

  • 914
  • JWH

    Here’s a thought:

    If the polls and RCP projections are both to be believed, we may end up with a president who earns a majority of votes in the electoral college, but whom the American people in general consider unworthy of the office.

    I would consider this a poor outcome regardless of whether Obama or Romney wins the race.

    • 914

      yeah, but we be a slight wee bit poorer if the golfer in chief putts around on the throne another 4 long decades..

  • Pingback: Forget the Polls – Obama Gets Crushed | Daily Pundit

  • http://www.facebook.com/people/Jack-Moss/100003560366510 Jack Moss

    There is also this from Gallup. The leader in the last pre-convention poll has gone on to win 12 of the last 15 elections. http://tinyurl.com/9cvym68

Optimization WordPress Plugins & Solutions by W3 EDGE