List-based samples are often biased because of coverage errors. The problem is especially acute in societies where the level of internal migration is high and where record keeping on the population is not reliable. We propose a solution based on spatial sampling that overcomes the inability to reach migrants in traditional area samples based on household lists. A comparison between a traditional study and our sample of Beijing demonstrates that coverage bias is greatly reduced. The successful incorporation of mobile urban residents has important substantive effects, in both univariate and multivariate analyses of public opinion data.

In this article I use linguistic fuzzy-set theory to analyze the process of decision making in politics. I first introduce a number of relevant elements of (numerical and linguistic) fuzzy-set theory that are needed to understand the terminology as well as to grasp the scope and depth of the approach. I then explicate a linguistic fuzzy-set approach (LFSA) to the process of decision making under conditions in which the decision makers are required to simultaneously satisfy multiple criteria. The LFSA approach is illustrated through a running (hypothetical) example of a situation in which state leaders need to decide how to combine trust and power to make a choice on security alignment.

Voting rights litigation requires ecological inference to estimate the voting preferences of minority and nonminority groups within the electorate. Double regression has been the procedure most commonly employed for this purpose. This article presents the first formal examination of this procedure. The underlying structural model reveals that double regression estimators are neither unbiased nor consistent estimators of true within-group vote preferences or polarization. Simulations demonstrate that they can substantially exaggerate the differences between minority and nonminority vote choices when none are present, and dramatically understate them when differences exist. In sum, double regression cannot meet conventional statistical standards for reliability. Consequently, it should be abandoned.

Of necessity, many tests for political influence on policies or outcomes involve the use of dummy variables. However, it is often the case that the hypothesis against which the political dummies are tested is the null hypothesis that the intercept is otherwise constant throughout the sample. This simple null can cause inference problems if there are (nonpolitical) intercept shifts in the data and the political dummies are correlated with these unmodeled shifts. Here we present a method for more rigorously testing the significance of political dummy variables in single equation models estimated with time series data. Our method is based on recent work on detecting multiple regime shifts by Bai and Perron. The article illustrates the potential problem caused by an overly simple null hypothesis, exposits the Bai and Perron model, gives a proposed methodology for testing the significance of political dummy variables, and illustrates the method with two examples.

Can researchers draw consistent inferences about the U.S. public's issue attitudes when studying survey results from both the in-person and telephone interview modes of the 2000 National Election Studies (NES) survey? We address this question through an analysis contrasting the distribution of issue attitudes across modes in the dual sample design of the 2000 NES. We find clear differences across mode even when applying a method devised by the NES to improve comparability by recoding issue attitude scales from the in-person mode. We present an alternative method of recoding these scales, which substantially improves comparability between modes. Through an analysis of the covariance structure of the issues and simple models of vote choice, we discuss the implications of the results for the study of issue attitudes in the 2000 NES.

In an earlier report, two of us (Bowers and Ensley, 2003, National Election Studies Technical Report, www.umich.edu/~nes) provided a general framework for understanding the particular strategy outlined by Fogarty et al. (in this issue). Fogarty et al.'s strategy is to make the face-to-face variables more like the random digit dial (RDD) telephone variables by trimming the ends in order to reduce the variance of the face-to-face (FTF) variables. Perhaps some scholars will want the FTF variables to look like the RDD variables, but that would be a fix for a specific research question. Given the significant differences in the representativeness of the samples, the processes of survey nonresponse, and the quality and character of the responses between data taken from a National Area Probability sample in person and data taken from an RDD telephone sample, research questions involving comparisons with other years in the 50-year time series will require different remedies.