In this paper, we develop and test a general measure of policy expenditures in the American states. Our approach is to construct a spatial proximity model of yearly state program spending. The empirical analysis reveals that state spending patterns vary along a clear and readily-interpretable unidimensional continuum which differentiates policies that provide particularized benefits to needy constituencies from policies that provide broader collective goods. Based upon standard evaluative criteria, the variable created from our model possesses some highly desirable characteristics. And, it compares favorably to other measures of state policy activity. The net result is a yearly score for each state which summarizes that state's spending across all major program areas. More generally, we believe that our variable can be interpreted as valid and reliable representational measurement of state policy priorities. In this capacity, it could occupy an important position within models of state politics.

In this paper I investigate the trade-off a legislature faces in the choice of instruments to ensure accountability by bureaucrats with private information. The legislature can either design a state-contingent incentive scheme or “menu law” to elicit the bureau's information or it can simply limit the set of choices open to the bureaucrat and let it choose as it wishes (an action restriction). I show that the optimal action restriction is simply a connected interval of the policy space. However, this class of instruments is not optimal without some sort of limitation on the set of levers of control available to the legislature. I then analyze one such limitation salient in politics, the legislative principal's inability to commit to honor a schedule of (state contingent) policy choices and transfer payments for a menu law. In this case the optimal action restriction outperforms (in terms of the legislature's welfare) the best available menu law.

Standard estimation procedures assume that empirical observations are accurate reflections of the true values of the dependent variable, but this assumption is dubious when modeling self-reported data on sensitive topics. List experiments (a.k.a. item count techniques) can nullify incentives for respondents to misrepresent themselves to interviewers, but current data analysis techniques are limited to difference-in-means tests. I present a revised procedure and statistical estimator called LISTIT that enable multivariate modeling of list experiment data. Monte Carlo simulations and a field test in Lebanon explore the behavior of this estimator.

Studies on national identity differentiate between nationalistic attitudes and constructive patriotism (CP) as two more specific expressions of national identity and as theoretically two distinct concepts. After a brief discussion of the theoretical literature, the following questions are examined: (1) Can nationalism and CP be empirically identified as two distinct concepts?; (2) Is their meaning fully or partially invariant across countries?; and (3) Is it possible to compare their means across countries? Data from the International Social Survey Program (ISSP) 2003 National Identity Module are utilized to answer these questions in a sample of 34 countries. Items to measure nationalism and CP are chosen based on the literature, and a series of confirmatory factor analyses to test for configural, measurement (metric), and scalar invariance are performed. Full or partial metric invariance is a necessary condition for equivalence of meaning across cultures and for a meaningful comparison of associations with other theoretical constructs. Scalar invariance is a necessary condition for comparison of means across countries. Findings reveal that nationalism and CP emerge as two distinct constructs. However, in some countries, some items that were intended to measure one construct also measure the other construct. Furthermore, configural and metric invariance are found across the full set of 34 countries. Consequently, researchers may now use the ISSP data to study relationships among nationalism, CP, and other theoretical constructs across these nations. However, the analysis did not support scalar invariance, making it problematic for comparing the means of nationalism and CP across countries.

This paper replicates and extends Groseclose, Levitt, and Snyder, “Comparing Interest Group Scores Across Time and Chambers: Adjusted ADA Scores for the U.S. Congress,” which appeared in the American Political Science Review (1999/93:33–50). We replicate the most recent unpublished extension by Dr. Groseclose and research assistants for years 1947–1999, and then we extend the analysis to include years 2000 through 2007. We make available inflation-adjusted ADA scores from 1947 through 2007, allowing scholars to incorporate the most recent interest group scores into their analyses.

We evaluate two diagnostic tools used to determine if counterfactual analysis requires extrapolation. Counterfactuals based on extrapolation are model dependent and might not support empirically valid inferences. The diagnostics help researchers identify those counterfactual “what if” questions that are empirically plausible. We show, through simple Monte Carlo experiments, that these diagnostics will often detect extrapolation, suggesting that there is a risk of biased counterfactual inference when there is no such risk of extrapolation bias in the data. This is because the diagnostics are affected by what we call the n/k problem: as the number of data points relative to the number of explanatory variables decreases, the diagnostics are more likely to detect the risk of extrapolation bias even when such risk does not exist. We conclude that the diagnostics provide too severe a test for many data sets used in political science.

In response to the data-based measures of model dependence proposed in King and Zeng (2006), Sambanis and Michaelides (2008) propose alternative measures that rely upon assumptions untestable in observational data. If these assumptions are correct, then their measures are appropriate and ours, based solely on the empirical data, may be too conservative. If instead, and as is usually the case, the researcher is not certain of the precise functional form of the data generating process, the distribution from which the data are drawn, and the applicability of these modeling assumptions to new counterfactuals, then the data-based measures proposed in King and Zeng (2006) are much preferred. After all, the point of model dependence checks is to verify empirically, rather than to stipulate by assumption, the effects of modeling assumptions on counterfactual inferences.