Essays in the measurement of public opinion
- This dissertation consists of three chapters that each deal with the optimal measurement and administration of public opinion surveys. In the first set of studies, I look at the measurement, and consequently, the meaning, of a key construct in public opinion research: liberal-conservative ideology. I argue that the standard item conflates two related, but separate constructs: liberal-conservative ideology and liberal-conservative identity. I test this notion by showing that those that say they are liberal or conservative act in a way that is consistent with social identity theory, i.e., they demonstrate a readiness to adopt the attitudes of other group members and consider themselves as interchangeable members with other liberals and conservatives, respectively. Furthermore, this identity has a substantive effect on at person's policy preferences, even after controlling for that person's ideological principles and party identity. In the next chapter I investigate the measurement of subjective probabilities. Participants are sometimes asked to respond using verbal response options, such as, "very likely" and "very unlikely, " and other times asked to respond using numerical response options, such as "0%" or "100%." Since data quality is contingent on the validity of the measures, guidelines are needed so that researchers write the best possible question to gauge perceptions of probabilities. Using three datasets, and a variety of analytic techniques, I show that percent chance questions are problematic in that they do not display a consistent linear or monotonic relationship with criterion question to which they should be linearly and monotonically related. In addition, although some argue that that verbally-labeled response scales are too coarse, respondents do not use 9/10ths of percent chance scales. Percent chance questions take longer to answer than verbally-labeled questions, and this difference is moderated by the cognitive ability of the respondent. However, only unipolar response scales yield higher concurrent validity than percent chance questions. The final chapter in this dissertation investigates the role of anonymity in the measurement of self-reports. Studies have shown that allowing people to answer questionnaires completely anonymously yields more reports of socially inappropriate attitudes, beliefs, and behaviors, and researchers have often assumed that this is evidence of increased honesty. But such evidence does not demonstrate that reports gathered under completely anonymous conditions are more accurate. Three studies reported in this chapter demonstrate that allowing college student participants to answer questions completely anonymously sometimes increased reports of socially undesirable attributes, but consistently reduced reporting accuracy and increased survey satisficing. These studies suggest that complete anonymity may compromise measurement accuracy rather than improve it.
|Type of resource
|electronic; electronic resource; remote
|1 online resource.
|Stanford University, Department of Communication
|Krosnick, Jon A
|Krosnick, Jon A
|Sniderman, Paul M
|Sniderman, Paul M
|Statement of responsibility
|Submitted to the Department of Communication.
|Thesis (Ph.D.)--Stanford University, 2012.
- © 2012 by Yphtach Lelkes
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...