Disclaimer. Don't rely on these old notes in lieu of reading the literature, but they can jog your memory. As a grad student long ago, my peers and I collaborated to write and exchange summaries of political science research. I posted them to a wiki-style website. "Wikisum" is now dead but archived here. I cannot vouch for these notes' accuracy, nor can I even say who wrote them. If you have more recent summaries to add to this collection, send them my way I guess. Sorry for the ads; they cover the costs of keeping this online.
Carsey, Thomas M.; Harden, Jeffrey J. 2010. New Measures of Partisanship, Ideology, and Policy Mood in the American States. State Politics and Policy Quarterly 10 (summer): 136-156.
Over the years, political scientists have come up with lots of different ways to measure each state's relative ideology. We all have a general sense that Utah, Idaho, and Mississippi lie to the right of Massachusetts, Hawaii, and California, but it's helpful to put exact numbers on those differences.
Many folks have relied on Erikson, Wright, and McIver's seminal contribution. They combined hundreds of national polls together, taken over many years, in order to get large enough state-level samples to produce state-level estimates of ideology and whatnot.
Recently, Carsey and Harden have come up with an even easier way. In 2000 and 2004, the National Annenberg Election Surveys asked a huge national sample (in daily rolling samples) questions about politics, providing plenty of respondents in every state. And in 2006, the Cooperative Congressional Election Study did the same (but with a different sampling approach, of course).
Using those surveys, Carsey and Harden produced three state-level measures: State partisanship (Republican to Democratic), state ideology (liberal to conservative), and state "mood." The first two are straightforward: The authors simply aggregated across self-reported partisanship and ideology questions. The "mood" question is more interesting. Carsey and Harden ran factor analysis on a series of specific policy questions to identify each state's "mood."
These are useful data that will likely displace previous measures of state opinion. If nothing else, these data are more recent than existing measures.
Carsey and Harden's estimates of "mood" surely hinge critically on the policy questions included in the factor analysis: abortion, stem cell research, affirmative action, environmental policy, and immigration. Arguably, Americans can have distinct opinions about social policies (like these) and economic policies (unlike these). Levenduvsky and Pope measured each state's economic "mood" in a paper back in 2008. If I could get Carsey and Harden's data, I'd be curious to see whether their "mood" variable matches up with Levenduvsky and Pope's. (Unfortunately, Carsey and Harden's data have not shown up yet in the SPPQ data archive, but they should soon.) Update: The data are here.
On a related note, I find it interesting that states seem to score very differently on partisanship, ideology, and mood. Looking at 2006, Utah comes up as #1 most Republican in partisanship, #9 most conservative in ideology, and #17 most conservative in "mood." Meanwhile, Michigan is #1 most Democratic in partisanship, #11 most liberal in ideology, and #17 most liberal in mood.
Clearly, these three measures are picking up distinct aspects of public opinion. And that's a puzzle I'm interested in exploring further--if I can get my hands on the data.
Research by the same authors
Research on similar subjects