Politico has a story today on the Employee Free Choice Act, and how the numbers each side is citing aren't matching up very well:

• “Nearly three-quarters of the public — 73 percent — support the Employee Free Choice Act,” crows the AFL-CIO on its website.

• “Seventy-four percent of voters oppose the Employee Free Choice Act,” concludes research cited by the pro-business Coalition for a Democratic Workplace.

From an extensive New Yorker article on movie marketing:

Executives’ testing stories take divergent paths to the same punch line. Either they decided not to tamper with a “Pulp Fiction,” despite testing results invariably described as “the lowest scores in the studio’s history,” or they were confounded when an “Akeelah and the Bee” faltered commercially despite “the highest scores in the studio’s history.” In both scenarios, the numbers lied. “Testing is a sham,” one marketing consultant says. “All you’ve learned is what people thought of a movie they didn’t have to pay for. It does not mean they’re going to go pay for it.”

Read the whole thing; it's got a lot of interesting details about the guts of marketing.

I've been meaning to write about this all day, but I'm only just now getting around to it.  Apparently, the Battle For EFCA has escalated to the point that different groups are going to Ambinder and leaking their polling. Of course, it would be nice if they would leak the datasets, sampling information, etc., but what can you really expect?  Anyway, it looks like this post has some nuggets in here that make for interesting commentary on how to poll.

A lot of reporting on polls is pretty terrible, but this from Politico is kind of egregious.  See why beneath the fold...

Nate Silver has a solid look at two polls of the 2010 Alaska Senate primary, with a hypothetical matchup of Lisa Murkowski vs. everyone's favorite hockey mom.  The kicker? The two polls both show roughly a 25 point lead--for different candidates.  Read the whole thing.

(I meant to do this last week, but I was visiting family in Asia, and damn it, Firefox ate my post again. Sorry about that. - DD)

We left off talking about how important it is to know your client:

When you are doing research for someone, they are entrusting you to discover what they need to accomplish their goals. It's an incredible responsibility, and not one that you should take lightly.  In order to understand their needs, you have to understand them.  You have to understand their organizational mission, their history, their resources in addition to the parameters of your specific project.  Unless you know your client, all the time and resources you put into it will be for naught.

The goal was to leave off and use the absence to see what we could find.  We'll see what we found out under the flip.

When we started this site, we never meant to let our partisan identification get have anything to do with what we wrote about. After all, when writing about data, voter files, polling, journalism, microtargeting, Linux and other such things, you'd think that there would be plenty of material to write about.  And, well, there is, but to my eyes, the perpetrators of stupidity in polling are mostly on the otherside.

Today's lesson comes from that bastion of truth-seeking and truth-speaking integrity, the Editorial Pages of the Wall. St. Journal.  Known parrhesiast Stephen Moore decides to show us how not to read a poll.

There's more.

Via the always-excellent Future Majority, Pew Research has released a new report about the impact of missing cell-phone-only voters in telephone polling.

An analysis of six Pew surveys conducted from September through the weekend before the election shows that estimates based only on landline interviews were likely to have a pro-McCain tilt compared with estimates that included cell phone interviews. But the difference, while statistically significant, was small in absolute terms

There's more below the fold...

In the last installment of this series, I talked a bit about how I wanted to change this up.  Instead of pretending that we were going to be working on some imaginary Congressional race in Missouri, which was just impossible to simulate, we were going to simulate doing a project for The Rock and Roll Hall of Fame.   Since their donor base and primary sources of revenue come from senior citizens and baby boomers, they want to know what these people think of recent inductions into the Hall of Fame, what they think of recent exhibits and what directions that they think that Hall should explore.

There's more.

I'd like to follow up on Pluribus' brilliant post on downloading and using census data with an explanation of how these data can be useful to you from a polling perspective. You're starting to see some of this happen with voter file vendors, but, hey, remember, the point of this site is to help smaller groups who can't afford a Catalist subscription do all the crazy fun data things that we do. 

There's more.