In this paper I present a class of discrete choice models for ordinal response variables based on a generalization of the stereotype model. The stereotype model can be derived and generalized as a random utility model for ordered alternatives. Random utility models can be specified to account for heteroscedastic and correlated utilities. In the case of the generalized stereotype model this includes category-specific random effects due to individual differences in response style. But unlike standard random utility models the generalized stereotype model is better suited for ordinal response variables and can be interpreted as a kind of unidimensional unfolding model. This paper discusses the specification, interpretation, identification, and estimation of generalized stereotype models. Two applications are provided for illustration.

This paper proposes a general approach to accounting for individual differences in the extreme response style in statistical models for ordered response categories. This approach uses a hierarchical ordinal regression modeling framework with heterogeneous thresholds structures to account for individual differences in the response style. Markov chain Monte Carlo algorithms for Bayesian inference for models with heterogeneous thresholds structures are discussed in detail. A simulation and two examples based on ordinal probit models are given to illustrate the proposed methodology. The simulation and examples also demonstrate that failing to account for individual differences in the extreme response style can have adverse consequences for statistical inferences.

Given the dramatic growth in the financial burden of cancer care over the past decades, individuals with cancer are increasingly susceptible to developing social needs (e.g., housing instability and food insecurity) and experiencing an adverse impact of these needs on care management and health outcomes. However, resources required to connect individuals with needed social and community services typically exceed the available staffing within clinical teams. Using input from focus groups, key informant interviews, user experience/user interface testing, and a multidisciplinary community advisory board, we developed a new technology solution, ConnectedNest, which connects individuals in need to community based organizations (CBOs) that provide services through direct and/or oncology team referrals, with interfaces to support all three groups (patients, CBOs, and oncology care teams). After prototype development, we conducted usability testing, with participants noting the importance of the technology for filling a current gap in screening and connecting individuals with cancer with needed social and community services. We employ a patient-empowered approach that engages the support of an individual’s healthcare team and community organizations. Future work will examine the integration and implementation of ConnectedNest for oncology patients, oncology care teams, and cancer-focused CBOs to build capacity for effectively addressing distress in this population.

The calibration of probability or confidence judgments concerns the association between the judgments and some estimate of the correct probabilities of events. Researchers rely on estimates using relative frequencies computed by aggregating data over observations. We show that this approach creates conceptual problems, and may result in the confounding of explanatory variables or unstable estimates. To circumvent these problems we propose using probability estimates obtained from statistical models—specifically mixed models for binary data—in the analysis of calibration. We illustrate this methodology by re-analyzing data from a published study and comparing the results from this approach to those based on relative frequencies. The model-based estimates avoid problems with confounding variables and provided more precise estimates, resulting in better inferences.

In recent years, a variety of efforts have been made in political science to enable, encourage, or require scholars to be more open and explicit about the bases of their empirical claims and, in turn, make those claims more readily evaluable by others. While qualitative scholars have long taken an interest in making their research open, reflexive, and systematic, the recent push for overarching transparency norms and requirements has provoked serious concern within qualitative research communities and raised fundamental questions about the meaning, value, costs, and intellectual relevance of transparency for qualitative inquiry. In this Perspectives Reflection, we crystallize the central findings of a three-year deliberative process—the Qualitative Transparency Deliberations (QTD)—involving hundreds of political scientists in a broad discussion of these issues. Following an overview of the process and the key insights that emerged, we present summaries of the QTD Working Groups’ final reports. Drawing on a series of public, online conversations that unfolded at www.qualtd.net, the reports unpack transparency’s promise, practicalities, risks, and limitations in relation to different qualitative methodologies, forms of evidence, and research contexts. Taken as a whole, these reports—the full versions of which can be found in the Supplementary Materials—offer practical guidance to scholars designing and implementing qualitative research, and to editors, reviewers, and funders seeking to develop criteria of evaluation that are appropriate—as understood by relevant research communities—to the forms of inquiry being assessed. We dedicate this Reflection to the memory of our coauthor and QTD working group leader Kendra Koivu.1

Studies were conducted in 1988, 1989, and 1992 in Plains, GA to measure effects of paraquat and alachlor on ‘Florunner’ peanut. Peanut treated with paraquat (0.14 kg ai/ha) plus alachlor (3.4 kg ai/ha) applied at vegetative emergence (VE), or paraquat plus alachlor VE followed by paraquat 28 days after emergence (DAE) were compared with a nontreated control. Both herbicide treatments reduced peanut foliage biomass at 65 DAE in 1989 and 1992. Herbicide treatments did not affect foliage biomass 90 DAE in 1988 and 122 DAE in 1989, but paraquat plus alachlor followed by paraquat reduced foliage biomass at 122 DAE in 1992. Pod biomass, measured at 90 and 65 DAE in 1988 and 1992, respectively, was reduced by herbicides. However, pod biomass did not differ among treatments 122 DAE in 1989 and 1992. Percent reflectance from the peanut canopy measured no effects from herbicides in 1988. However, in 1989 and 1992 herbicides applied sequentially reduced peanut canopy development. Peanut treated with a single herbicide and sequentially took longer to mature. Once optimum maturity was reached, peanut yields were not reduced.

The evolution of glyphosate resistance in weedy species places an environmentally benign herbicide in peril. The first report of a dicot plant with evolved glyphosate resistance was horseweed, which occurred in 2001. Since then, several species have evolved glyphosate resistance and genomic information about nontarget resistance mechanisms in any of them ranges from none to little. Here, we report a study combining iGentifier transcriptome analysis, cDNA sequencing, and a heterologous microarray analysis to explore potential molecular and transcriptomic mechanisms of nontarget glyphosate resistance of horseweed. The results indicate that similar molecular mechanisms might exist for nontarget herbicide resistance across multiple resistant plants from different locations, even though resistance among these resistant plants likely evolved independently and available evidence suggests resistance has evolved at least four separate times. In addition, both the microarray and sequence analyses identified non–target-site resistance candidate genes for follow-on functional genomics analysis.

We construct the complete network of 26,681 majority opinions written by the U.S. Supreme Court and the cases that cite them from 1791 to 2005. We describe a method for using the patterns in citations within and across cases to create importance scores that identify the most legally relevant precedents in the network of Supreme Court law at any given point in time. Our measures are superior to existing network-based alternatives and, for example, offer information regarding case importance not evident in simple citation counts. We also demonstrate the validity of our measures by showing that they are strongly correlated with the future citation behavior of state courts, the U.S. Courts of Appeals, and the U.S. Supreme Court. In so doing, we show that network analysis is a viable way of measuring how central a case is to law at the Court and suggest that it can be used to measure other legal concepts.