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 say who wrote them.
Stimson. 1991. Public opinion in America: Moods, cycles, and swings. Boulder: Westview Press.
This summary is based only on Chapter 1.
Many studies of "public" opinion are actually studying (individual-level) "private" opinion--they are studying what types of people think, and why. Stimson wants to study aggregate public opinion over time. He's not interested in discontinuities (sudden changes in opinion), he's interested in "changes at the margins," or TRENDS (the public MOOD)--a continuous movement in a single direction, perhaps with small increments. It's only a trend if the movement is in a single direction for a long time; otherwise, it's a mere "drift." He's also interested only in our opinions on "real" issues (i.e. what policy to adopt), not "valence" issues (i.e. symbolic or emotional issues, or "is the economy doing well").
Thus, for him, each survey is a unit of analysis (not each respondent). Y: the trends.
From the bottom of p 4:
Tourists come to the mountains and are awed by its large, majestic features. Geologists, on the other hand, pull out their magnifying glasses to look at only a few inches of the mountains, from which they can make important conclusions about where the mountains came from and how long they've existed. Many public opinion researchers are like the geologists, but Stimson wishes to take a broader view of public opinion. Thus, Stimson will focus on "politics at the margins"--the small, seemingly unimportant changes that lead to big long-run effects (mountains).
Although Stimson recognizes the value of Mayhew's assumption that politicians are motivated only by reelection, he criticizes political scientists for ceasing to question this assumption. It is useful in certain circumstances, but it cannot explain why some people choose to become politicians in the first place. For the purposes of this study, he adopts a different assumption: Politicians are motivated by a desire to lead public opinion. Sometimes they follow it, but sometimes they lead it.
Includes lots of questions that can be placed along a left-right continuum. The questions aren't consistently the same, so he uses subsets. He finds a set of questions that were asked in T1 and T2, then compares them. Then he finds another set from T2 and T3, and compares them. So he can form a measure of mood that spans many surveys and multiple questions.
Mood swings happen when politicians go too far out of the zone of acquiescence, prompting a backlash. Conservative policies create demand for liberal policies, and vice versa.
Research by the same authors
Research on similar subjects