Which poll to believe?

[bulletandpima]

<p>So on the drudge today they had 3 different polls…my question is which one do we believe?</p>

<p>Gallup

Barack Obama’s lead over John McCain has settled back slightly to a 48% to 40% margin among registered voters in Gallup Poll Daily tracking conducted July 25-27

</p>

<p>Rasmussen

Obama now attracts 45% of the vote while John McCain earns 42%. When “leaners” are included, it’s Obama 48% and McCain 45%. Both Obama and McCain are viewed favorably by 56% of voters

</p>

<p>MY favorite…not b/c McCain is ahead, but becuse Gallup did it with USA Today…how can they have Obama up 8 pts. and down 4 pts in the same period?

Republican presidential candidate John McCain moved from being behind by 6 points among “likely” voters a month ago to a 4-point lead over Democrat Barack Obama among that group in the latest USA TODAY/Gallup Poll

</p>

<p>All on the same day!</p>

<p>I have to agree that Obama did a phenomenal job in Europe, but it is not translating in the polls. It is now becoming well Jimmy Carter was up 30+ in July against Ford and in the end they needed another day to declare him the winner. Dukakis was up against Bush 41, but lost. Bush 43 was down against Gore and Kennedy at this time and won. </p>

<p>I am just not getting how he can sell out stadiums, be awed by the media and the world, yet he can’t seem to translate it in polls regarding likely voters!</p>

<p>I also can’t get how Gallup has 2 different polls released on the same day with a 12 pt difference!</p>

<p>[Why</a> is Obama not improving in the polls? - International Herald Tribune](<a href=“http://www.iht.com/articles/2008/07/28/america/obama.php]Why”>http://www.iht.com/articles/2008/07/28/america/obama.php)</p>

[ucsd_ucla_dad]

<p>Most people just believe the poll that fits their ‘side’ the best. I don’t pay any attention to them.</p>

[Newjack88]

<p>I’m with ucsd<em>ucla</em>dad. But a general rule of thumb is to always go with the one that polls registered voters.</p>

[calmom]

<p>

There is no agreed upon way of determining likely voters, and generally every polling organization that reports on this group uses distinct procedures. Over the years, there has been debate – sometimes vigorous – on the relative merits of one procedure compared to another.</p>

<p>Gallup has a general set of ways of determining likely voters, which have proved to be quite accurate in past congressional and presidential elections. Voters are asked a series of questions about their interest in the election, their plans to vote, and their previous history in voting. The total sample is then divided into two groups: One group is made up of the 60% of voters who score the highest on these measures and are therefore considered most likely to vote, and the other group is composed of voters who are less likely to vote. (The 60% estimate can vary depending on information about likely turnout.)</p>

<p>At this point, the USA Today/Gallup poll is using a set of three questions to determine likely voters:</p>

<ol>
<li><p>How much thought have you given to the upcoming election for president – quite a lot, or only a little?</p></li>
<li><p>How often would you say you vote – always, nearly always, part of the time, or seldom?</p></li>
<li><p>Do you, yourself, plan to vote in the presidential election this November, or not?

Source: [Who</a> Are Likely Voters and When Do They Matter?](<a href=“Who Are Likely Voters and When Do They Matter?”>Who Are Likely Voters and When Do They Matter?)</p></li>
</ol>

<p>Obviously, question #2 would tend to screen out the strongest Obama demographic – the young voters, many of whom were too young to vote in the last presidential election and for various reasons are less likely to vote in local elections. </p>

<p>I think question #1 is also a problem – because there are a lot of Obama supporters who don’t have to give very much thought to choice between Obama & McCain, especially among those who strongly oppose the Iraq war. </p>

<p>The question that Gallup should have asked, but didn’t ask, was how enthusiastic the voters felt about the candidate – definitely as an offset or supplemental question to #1. </p>

<p>Bottom line When you see conflicting results for “likely” voters, keep in mind that this is a screen that is inconsistent between polls, and it is also one that is a very easy way to inject bias into poll results, whether or not such bias is intentional.</p>