jump to navigation

Pollster biases revealed November 3, 2008

Posted by Sverre in : Methods in political science, US Presidential election , add a comment

The Monkey Cage led me to a paper by Len Adleman and Mark Schiling that compares the election polls made by American networks. They’ve compared them to the polls made by Gallup And Rasmussen, and show that the political inclination of the networks seem to influence the polls. Fox’s polls show a trend of predicting more to the right, and CBS/NYT more to the left. This is really interesting.

I agree with Andrew Gelman who comments that this surprises him. I would expect their coverage of the polls to show some bias, but had expected the polls themselves to be done in a professional way eliminating personal biases. This apparently goes to show that being completely neutral is difficult if not impossible, even in quantitative analysis.

What if the whole world could vote? October 30, 2008

Posted by Sverre in : Methods in political science, US Presidential election , 12comments

asks the Economist and tests it. They’ve asked their online readers to vote and constructed a worldwide electoral college. Lo and behold! the world electorate map is shockingly enough painted bright blue. It appears most nations in the world have a distribution in excess of 80-20 in Obama’s favour. Some people (no serious political scientists I hope) take this as evidence that the world supports Obama.

Economist.com voter map screenshot

Economist.com voter map screenshot

The world at large probably prefers Obama, but this “survey” does in no way confirm that. Why not? It’s really quite simple. The survey is conducted at the Economist.com website. And who are going to claim that worldwide readers of the Economist represent a fair approximation to a random distribution of the population? None, I hope. For example, I would expect the Economists’ readers to have vastly higher than average levels of education. This is further accentuated by the fact that not every visitor to the website can vote, just registered Economist.com members. This ensures that even those casual visitors not normally reading the Economist are even less likely to vote.

There is no easier way to prove the bias of the survey than just looking at the scores for the US in this survey. In this survey the US supports Obama by 81-19.

This isn’t even very original. I have seen several such maps made on the basis of different surveys already, and must have read a dozen different online articles on it.

So has the Economist suddenly gone naive and stupid? Of course not. This was never intended as a survey by the Economist, so just don’t make the mistake of treating it like one. What the Economist wanted was more hits to their website, and more registered members on their website. I’d guess this got them hundreds, if not thousands. It worked on me. 😉 (more…)

Has Obama already won? October 19, 2008

Posted by Sverre in : US Presidential election , 3comments

Obama has had a good lead on the polls for a few days now – does this mean he’s won? Here’s a side glance at what the internet thinks.

Yes, say Norwegian newspapers. The reason they all agree is of course because they all quote their favourite expert, professor Ole O. Moen from the University of Oslo. To Dagsavisen, for example, he says he thinks it will now take a real or imagined terror threat for Obama to lose. He doesn’t think Obama is going to make any big enough mistakes.  But with a single expert being quoted across the board I thought I’d look around a bit.

I assumed I could rely on Fox News to bring me predictions that didn’t favour that black yuppie, but their website did little more than confuse me. They were more interested in telling me that the great-great-great-granddaughter of a slave on McCain’s ancestor’s farm is now a psychology professor.

The Washington Post seems to think Obama will win. Among other things, they can tell us how McCain’s got trouble with media as Obama gets all the endorsements and the great maverick himself is starting a fight with the NYT. Just in case the unthinkable should happen and McCain wins, the Post has posted (ha-ha) some emergency help to journalists to help explain it. At least they list possible reasons why things might take an unexpected turn. (more…)

Norwegian media loves Obama, but doesn’t hate McCain September 30, 2008

Posted by Sverre in : US Presidential election , add a comment

As I wrote about some days ago, I’ve been gathering data on the Norwegian media coverage of the US Presidential Election. I’m now up to date with all registering of data, and have taken a little more time to analyze it. With 154 registered articles, the main conclusion still stands: Norwegian media favours Barack Obama both in volume and in positivity of the coverage.

Current numbers (September 30th 2008):
Obama: 106 articles, +29 balance
McCain: 73 articles, -3 balance

It does however seem clear as well that this enthusiasm doesn’t translate into a campaign against McCain. The coverage of McCain’s campaign seems well-balanced, with the number of negatively and positively angled articles roughly balancing each other out. (more…)

Norwegian media loves Obama September 20, 2008

Posted by Sverre in : US Presidential election, World politics , add a comment

With an estimated 23.000 eligible American voters, it isn’t likely the American presidential election will be decided in Norway. Still, there is a great interest in it. USA’s decisions, especially with regards to the economy and foreign policy affect the entire world. This year I’ve started my own little informal and quasi-scientific research project to see how Norwegian media covers the American election.

My hypothesis is that Norwegian media would favor any Democratic candidate very strongly over his or her Republican counterpart. I assume this to be a representation of the general opinion of the Norwegian public. I further assume that in this election, this favoritism will benefit Barack Obama greatly.

Obama McCain
# of articles 96 50
Bias points 28 4
Data extracted on: 20. september 2008

As the table above shows, the data so far supports this hypothesis quite clearly. With about 130 articles entered, the Obama campaign appears to have had about twice the coverage the McCain campaign has as counted in the number of articles. Furthermore, the amount of of positive coverage outweighs the negative coverage for both candidates, but much more so for Obama than McCain.
(more…)

The awesome power of Oprah August 5, 2008

Posted by Sverre in : US Presidential election , add a comment

The Monkey Cage blogBarack and Oprah

brought my attention to an interesting and slightly disturbing paper by Craig Garthwaite and Tim Moore of Maryland University. They have analyzed the effect Oprah Winfrey’s endorsement of Barack Obama has had on his campaign. And it appears Mrs. Winfrey really deserves her places on Forbes’ lists of the 100 most influential people in the world.

Firstly, their research method is quite ingenious. Among other things they’ve looked at the sales of books recommended in Oprah’s bookclub to measure the level of influence she holds over consumer attitudes in different areas. This is interesting enough on its own when they report that the sale of Tolstoy’s Anna Karenina increased from nearly 12,000 copies before her endorsement to 650,000 copies afterwards!

The authors, both economists, present a formal (aka. mathematical) model for calculating the effect of the endorsement based on models about the effect of endorsements by interest groups.

Comparing this measure and others with election results from the primaries gives a good indication about where and how much Oprah’s endorsement was worth for Obama. And quite disturbingly they estimate that it gained him between 400,000 and 1,6 million votes(!).

Furthermore, the lower bound of that estimate is higher than the number of votes Obama beat Clinton by in the states that were included in the sample. The data thus might be interpreted to indicate that Oprah’s endorsement was the deciding factor in Obama’s victory over Clinton….

This is an economists’ approach to the subject, but the very well documented paper is at least food for thought…

Read the entire paper here: http://www.econ.umd.edu/~garthwaite/celebrityendorsements_garthwaitemoore.pdf