This article presents a novel automatic method of text analysis aimed at discovering patterns of lexical cohesion in political speech. The unit of analysis are groups of words with related meanings; the software is based on the results of a multiperson annotation experiment that captures reliably identified connections between words in a text. We illustrate the advantages of such a representation by juxtaposing results of a detailed hand-made analysis of Margaret Thatcher's rhetoric with analysis based on the automatically detected groups of words. We both corroborate previous findings regarding Thatcher's rhetorical tools and illuminate additional elements thereof. We suggest that lexical cohesion analysis is a promising technique to bridge the gap between quantitative and qualitative analyses of text as political material, by establishing units that are both robust enough to enable comprehensive coverage and coherent enough to support direct interpretation.

In a recent article in the American Political Science Review, Laver, Benoit, and Garry (2003, “Extracting policy positions from political texts using words as data,” 97:311—331) propose a new method for conducting content analysis. Their Wordscores approach, by automating text-coding procedures, represents an advance in content analysis that will potentially have a large long-term impact on research across the discipline. To allow substantive interpretation, the scores produced by the Wordscores procedure require transformation. In this note, we address several shortcomings in the transformation procedure introduced in the original program. We demonstrate that the original transformation distorts the metric on which content scores are placed—hindering the ability of scholars to make meaningful comparisons across texts—and that it is very sensitive to the texts that are scored—opening up the possibility that researchers may generate, inadvertently or not, results that depend on the texts they choose to include in their analyses. We propose a transformation procedure that solves these problems.

Chiou and Rothenberg raise important questions about how to measure key concepts in the study of legislative stalemate in the U.S. Congress. In challenging my choice of measures to capture bicameral differences, Chiou and Rothenberg argue that my findings are the artifact of measurement error. In this reply, I review the hurdles involved in measuring policy views over time and across institutions and suggest that the preferred measure of Chiou and Rothenberg falls short for measuring bicameral differences. Second, I assess the extent to which measurement choices affect the robustness of my findings about the determinants of gridlock. Drawing on new measures and model specifications, I show that my results are robust to alternative specifications. I conclude with an assessment of the broader challenges posed by how we measure critical concepts in the study of congressional performance.

In this paper, we introduce a recently developed methodology for assessing the assumption of causal homogeneity in a time series cross-section Granger framework. Following a description of the procedure and the analytical contexts for which it is appropriate, we implement this new approach to examine the transformation of the post-World War II party system in the South. Specifically, we analyze the causal relationship between black mobilization and GOP growth in the region. We find that black mobilization Granger caused Republican growth throughout the South, whereas Republican growth Granger caused black mobilization only in the deep South. We discuss the substantive significance of our results and conclude with guidelines for the appropriate use of this procedure and suggestions for future extensions of the method.

In “A Robust Transformation Procedure,” Martin and Vanberg (2007, hereafter MV) propose a new method for rescaling the raw virgin text scores produced by the “Wordscores” procedure of Laver, Benoit, and Garry (2003, hereafter LBG). Their alternative method addresses two deficiencies they argue exist with the transformation of virgin text scores proposed by LBG: First, that the LBG transformation is sensitive to the selection of virgin texts, and second, that it distorts the reference metric by failing to recover the original reference scores when reference texts are scored and transformed as if they were virgin texts. Their proposed alternative is “robust” in the sense that it avoids both shortcomings. Not only is MV's transformation a welcome contribution to the Wordscores project but also the critical analysis on which it is based brings to light a number of assumptions and choices that face the analyst seeking to estimate actors' policy positions using statistical analyses of the texts they generate. When first describing the possibility of rescaling the raw virgin text estimates, we emphasized that our

This article describes a new machine-coded event data set specifically designed to study the spatially, temporally, and tactically disaggregated actions of multiple state and nonstate actors in a systematic fashion. The project develops an extensive set of dictionaries for multiple actors and employs a new coding scheme to organize information on such actors and their behavior. The author describes the machine content-analysis methods used to collect the data and the newly developed coding scheme.

In a recent issue of this journal, Larocca (2005) makes two notable claims about the best linear unbiasedness of ordinary least squares (OLS) estimation of the linear regression model. The first, drawn from McElroy (1967), is that OLS remains best linear unbiased in the face of a particular kind of autocorrelation (constant for all pairs of observations). The second, much larger and more heterodox, is that the disturbance need not be assumed uncorrelated with the regressors for OLS to be best linear unbiased. The assumption is unnecessary, Larocca says, because “orthogonality [of disturbance and regressors] is a property of all OLS estimates” (p. 192). Of course OLS's being best linear unbiased still requires that the disturbance be homoskedastic and (McElroy's loophole aside) nonautocorrelated, but Larocca also adds that the same automatic orthogonality obtains for generalized least squares (GLS), which is also therefore best linear unbiased, when the disturbance is heteroskedastic or autocorrelated.

Binder (n.d., Taking the measure of Congress: Reply to Chiou and Rothenberg. Political Analysis. Forthcoming) highlights areas of agreement and disagreement with our discussion of preference measurement and legislative gridlock. We now both agree that W-NOMINATE scores—employed in Binder (1999, The dynamics of legislative gridlock. American Political Science Review 9:519–33) to measure key independent variables, including bicameral differences—should not be used when examining multichamber legislatures over time. We continue to disagree over whether Common Space scores or Binder's conference vote measure is superior. In this response, we show that, although several of the theoretical and statistical objections that Binder (n.d.) raises to our Common Space measure do not apply, they are all relevant for her conference vote analog. Additionally, we detail how, despite protests to the contrary, the conference vote measure is plagued by insufficient data. Finally, we demonstrate how new efforts to show that Binder's (1999) results continue to hold are not robust.

We appreciate the positive reception of our transformation by Benoit and Laver (hereafter, BL), and we are grateful that they have incorporated it into the Wordscores package. Because their comment highlights a fundamental difference between the Martin-Vanberg (MV) and Laver-Benoit-Garry (LBG) approaches that is critical to the choice among transformations, we offer some brief comments that will allow users to make an informed decision regarding the appropriate use of the transformations. The central issue concerns comparisons between reference and virgin texts. As BL point out, researchers will often be interested in making such comparisons, and the LBG and MV transformations can yield substantially different results. In light of these differences, BL's primary suggestion is to focus analysis on the raw scores, which can be obtained for reference as well as virgin texts. We wholeheartedly agree with this prescription. In fact, it is precisely a concern for faithfully reporting the raw score information, while making it more intuitive, that motivates the MV transformation. As we show below, the MV transformation accurately reflects all and nothing but the information contained in raw scores. Therefore, “users [who] get eye strain” by looking at raw scores can safely substitute MV scores and be confident that the information provided is equivalent. The same will typically not be true of LBG scores.