Looking for party registration statistics for the 31 states plus D.C. that track them in official records? We've got 'em. Nate Silver reflects on the fallibility of new and novel datasets. And we forecast at least four more months of arguing over which Senate forecast is right. This is HuffPollster for Tuesday, May 27, 2014.
PARTISAN AFFILIATION BY STATE - With the 2014 elections approaching, arguments over the partisan composition of polls are inevitable, as is the perennial confusion over party identification and party registration. Most opinion pollsters measure the former with this question (or a closer variant): "Generally speaking, you usually think of yourself as a Republican, a Democrat, an Independent, or what?" But the partisan affiliation that some voters provide when they register to vote is something different. [see also HuffPost, 2012, Brennan Center]
To help prepare for our coverage, HuffPost's Stephen Calabria compiled the most recent official registration statistics from 31 states plus the District of Columbia that enable voters to pick a party upon registering to vote. One immediately obvious characteristic of the data is the huge variability in percentage of voters who remain unaffiliated or unclassified, from a low of 8 percent in Kentucky to a high of 92 percent in Arkansas. One cause for that variability is the degree to which individual states limit primary voting to those formally affiliated with a particular party. These differences also help explain why voters often say one thing when asked how they are registered and another when asked what party they feel closer to. [Registration data spreadsheet]
LESSONS ABOUT DATA FROM THE PIKETTY CONTROVERSY - Nate Silver: "Data never has a virgin birth. It can be tempting to assume that the information contained in a spreadsheet or a database is pure or clean or beyond reproach. But this is almost never the case....And it’s important to keep expectations in check when a controversy like the one surrounding the French economist Thomas Piketty arises...Science is messy, and the social sciences are messier than the hard sciences. Research findings based on relatively new and novel data sets (like Piketty’s) are subject to one set of problems — the data itself will have been less well scrutinized and is more likely to contain errors, small and large. Research on well-worn datasets are subject to another. Such data is probably in better shape, but if researchers are coming to some new and novel conclusions from it, that may reflect some flaw in their interpretation or analysis. The closest thing to a solution is to remain appropriately skeptical, perhaps especially when the research finding is agreeable to you." 
WHY FORECASTS GIVE DIFFERENT ODDS OF A GOP SENATE TAKEOVER? - Overheard on Twitter on Tuesday:
-Political scientist Alan Abramowitz: "NYT Upshot and WP Monkey Cage forecasts are giving very different odds of R takeover of Senate: 41% vs. 77%. Why? Upshot uses state polls." [@AlanIAbramowitz]
-FiveThirtyEight's Harry Enten: "I have the state polls as well... Combining the two, I feel like the truth is in-between http://t.co/kUwaml7MZ4" [@ForecasterEnten]
-HuffPost's Natalie Jackson: "Probably more differences in coding & decisions between the models than just state polls..." [@nataliemjb]
-NYT Upshot's Nate Cohn: "there are a surprising number of different choices." [@Nate_Cohn; see also posts from early may by Cohn and the Upshot team and by John Sides of WashPost's Monkey Cage explaining differences in the models].
-Related reminder to DC area readers: Tomorrow (Wednesday May 28) at 11:30 a.m., HuffPollster will join political scientists Matthew Dickenson, Michael Lewis-Beck, Drew Linzer, Mary Stegmaier and Lynn Vavreck for a briefing on election forecasting sponsored by the American Political Science Association at the Dirksen Senate Office Building in Washington DC on May 28. [APSA]
HUFFPOLLSTER VIA EMAIL! - You can receive this daily update every weekday via email! Just click here, enter your email address, and and click "sign up." That's all there is to it (and you can unsubscribe anytime).
TUESDAY'S 'OUTLIERS' - Links to the best of news at the intersection of polling, politics and political data:
-A new Florida survey finds Rick Scott (R) nearly tied with challenger Charlie Crist (D). [SurveyUSA]
-A Repass poll finds Shelley Moore Capito (R) 11 points ahead of Natalie Tennant (D) in West Virginia. [Charleston Daily Mail]
-Rasmussen gives Jeff Merkley a 10-point lead over Monica Wehby in Oregon. [Oregon Live]
-A Honolulu Civil Beat poll shows Brian Schatz leading Colleen Hanabusa in Hawaii's Democratic Senate primary. [HuffPost]
-Gary King narrowly leads New Mexico's Democratic gubernatorial primary. [Albuquerque Journal]
-Polling suggests Americans would support the Afghanistan draw-down announced by President Obama on Tuesday. [NYTimes]
-Philip Bump doesn't expect millennials' surging numbers to have much impact at the polls. [WashPost]
-Sean Sullivan compiles a list of five things to watch in the Texas runoffs. [WashPost]
-Eric Ostermeier says Texas Rep. Ralph Hall could be vulnerable in his runoff race. [Smart Politics]
-Harry Enten creates a profile of what a Democratic challenger to Hillary Clinton might look like. 
CORRECTION: An earlier version of the spreadsheet in this post transposed the Democratic and Republican registration numbers for Nebraska.