Over the last 15 years a large amount of scholarship in legislative politics has used NOMINATE or other similar methods to construct measures of legislators' ideological locations. These measures are then used in subsequent analyses. Recent work in political methodology has focused on the pitfalls of using such estimates as variables in subsequent analysis without explicitly accounting for their uncertainty and possible bias (Herron and Shotts 2003, Political Analysis 11:44–64). This presents a problem for those employing NOMINATE scores because estimates of their unconditional sampling uncertainty or bias have until now been unavailable. In this paper, we present a method of forming unconditional standard error estimates and bias estimates for NOMINATE scores using the parametric bootstrap. Standard errors are estimated for the 90th U.S. Senate in two dimensions. Standard errors of first—dimension placements are in the 0.03 to 0.08 range. The results are compared with those obtained using the Markov chain Monte Carlo estimator of Clinton et al. (2002, Stanford University Working Paper). We also show how the bootstrap can be used to construct standard errors and confidence intervals for auxiliary quantities of interest such as ranks and the location of the median senator.

In pursuing their goals, members of the U.S. Supreme Court are affected by their institutional setting. How has that institutional environment changed over time and what have been the political consequences of those changes? Despite considerable analysis of the institutional dynamics of legislatures and executives, political scientists have been slow to bring time series techniques to the study of the Supreme Court, and as a result much less is known about its evolutionary path. Measuring a variety of organizational characteristics, I construct an index of the institutionalization of the Supreme Court from 1790 to 1996. This indicator suggests that the integration of the Court into the system of federal policy making has better enabled the justices to satisfy their objectives. To demonstrate this empirically, I test a series of error correction models of judicial influence, each of which confirms that the nature of the Supreme Court's character has had considerable implications for the scope of the justices' legal and political impact. These results underscore the need for judicial scholars to examine the Court's policy making in longitudinal perspective.

This article argues that a key step in King's iterative approach to R × C ecological inference problems—the aggregation of groups into broad conglomerate categories—can introduce problems of aggregation bias and multimodality into data, inducing model violations. As a result, iterative EI estimates can be considerably biased, even when the original data conform to the assumptions of the model. I demonstrate this problem intuitively and through simulations, show the conditions under which it is likely to arise, and illustrate it with the example of Coloured voting during the 1994 elections in South Africa. I then propose an easy fix to the problem, demonstrating the usefulness of the fix both through simulations and in the specific South African context.

Despite the desire to focus on the interconnected nature of politics and economics at the global scale, most empirical studies in the field of international relations assume not only that the major actors are sovereign, but also that their relationships are portrayed in data that are modeled as independent phenomena. In contrast, this article illustrates the use of linear and bilinear random—effects models to represent statistical dependencies that often characterize dyadic data such as international relations. In particular, we show how to estimate models for dyadic data that simultaneously take into account: (a) regressor variables, (b) correlation of actions having the same actor, (c) correlation of actions having the same target, (d) correlation of actions between a pair of actors (i.e., reciprocity of actions), and (e) third-order dependencies, such as transitivity, clustering, and balance. We apply this new approach to the political relations among a wide range of political actors in Central Asia over the period 1989–1999, illustrating the presence and strength of second- and third-order statistical dependencies in these data.

This paper replicates the findings that appeared in the article “Severing the Electoral Connection: Shirking in the Contemporary Congress,” published in the American Journal of Political Science (44:316–325), in which Lawrence Rothenberg and Mitchell Sanders incorporated a new research design and, contrary to all previous studies, found evidence of ideological shirking in the U.S. House of Representatives. We investigate the robustness of their results by reestimating their model with Congress-specific fixed effects and find that their results no longer hold.

Research designs that call for the estimation of time trends in legislator ideal points must allow for changes in underlying policy spaces. Simply put, a set of legislator ideal points from one such space cannot necessarily be compared with a set of ideal points from another. Rothenberg and Sanders's (2000, American Journal of Political Science 44:316–325) analysis of shirking in Congress does not internalize this point insofar as it assumes that legislator ideal points from adjoining congressional sessions lie in a common space. While it may be the case that members of Congress shirk ideologically when approaching retirement, the regression estimates at the heart of Rothenberg and Sanders neither support this possibility nor constitute evidence against it.

While Herron (2004, Political Analysis 12:182–190) is correct that sensitivity to changes in underlying scale and how they affect estimates and inferences is generally important, our assumption in Rothenberg and Sanders (2000, American Journal of Political Science 44:310–319) that W-NOMINATE scales can be directly compared from one Congress to another to study legislative shirking is quite defensible because scale variability is not a substantial problem. Not only are the assumptions in our original analysis regarding variability very reasonable, because any variability is quite small, but effects on consistency are marginal and, to the degree that they are relevant, indicate that our test of the shirking hypothesis is conservative. Furthermore, even generous estimates of variability in W-NOMINATE between one immediate Congress and another have little impact on results. In addition, Herron's analysis includes an unaddressed censoring problem that again, while unlikely to have much substantive relevance, indicates that Rothenberg and Sanders have worked against themselves in trying to find shirking. In conclusion, the issues that Herron highlights are of marginal consequence for the original analysis and, to the extent they matter, only buttress the findings generated and the inferences drawn.

This study replicates and extends Groseclose's (1994) tests of Congressional committee composition hypotheses for the 99th Congress. Alternative hypotheses pit partisan explanations of committee organization against the informational roles committees can play in producing “good” public policy. Other hypotheses explore the likelihood that committees reflect (rather than diverge from) floor preferences. Predictably, empirical tests of such hypotheses have produced no scholarly consensus. Groseclose (1994) enters the debate by using Monte Carlo simulations to test alternative hypotheses of Congressional committee organization, and in so doing, he makes few assumptions (and specifically avoids problematic ones) about the ideological distribution of committee and floor members. For example, difference of means tests, often used to evaluate the significance of floorcommittee divergence, assume that preferences are distributed normally and that the mean scores of a committee and floor are the correct test statistics. Groseclose asserts that the normality assumption is less convincing for small committees and that the median score is more appropriate.

It is impossible to overstate the importance of doing original research based on primary source material in scientific analysis (see, for example, King 1995). Failing to consult primary sources, and by definition relying on secondary sources, can lead to incorrect analyses and mistaken conclusions. An exemplary case is the apparent mystery of whether justices strategically retire and exactly when Congress passed legislation allowing federal judges to retire with benefits upon reaching age 65. One study cited 1937 as the year and based its analysis of judicial retirement on this “fact” (Abraham 1975). Subsequent studies cited the original piece without ever checking the original data—in this case a federal statute—and “replicated” the same mistaken analyses (see Atkinson 1999). In fact, the actual year this legislation was passed was 1954. This 17-year error not only makes a significant difference in the analysis of judicial retirement decisions, but also shows the importance of verification and replication in political research.