Gaussian variational estimation for multidimensional item response theory

Multidimensional item response theory (MIRT) is widely used in assessment and evaluation of educational and psychological tests. It models the individual response patterns by specifying a functional relationship between individuals' multiple latent traits and their responses to test items. One major challenge in parameter estimation in MIRT is that the likelihood involves intractable multidimensional integrals due to the latent variable structure. Various methods have been proposed that involve either direct numerical approximations to the integrals or Monte Carlo simulations. However, these methods are known to be computationally demanding in high dimensions and rely on sampling data points from a posterior distribution. We propose a new Gaussian variational expectation--maximization (GVEM) algorithm which adopts variational inference to approximate the intractable marginal likelihood by a computationally feasible lower bound. In addition, the proposed algorithm can be applied to assess the dimensionality of the latent traits in an exploratory analysis. Simulation studies are conducted to demonstrate the computational efficiency and estimation precision of the new GVEM algorithm compared to the popular alternative Metropolis–Hastings Robbins–Monro algorithm. In addition, theoretical results are presented to establish the consistency of the estimator from the new GVEM algorithm.     

Not Simply in the Eye of the Beholder: Authenticity as a Product of Candidate Preference and Unfettered Speech

Authenticity has emerged over recent decades as a prominent theme in both the press and in political research—and peaked in the 2016 presidential contest that pitted Donald Trump against Hillary Clinton, Bernie Sanders, Marco Rubio, and Ted Cruz. In this context, we attempted to answer the question: How do voters judge a presidential candidate's authenticity? Here we use motivated reasoning and correspondent inference theory as theoretical frameworks to examine how partisan preference combines with perceptions of unfettered speech and strategic impression management to influence voter judgments of a candidate's authenticity. An online survey of 525 respondents demonstrated that individuals' partisan preferences influenced both judgments of a candidate's authenticity and their perceptions of behaviors signifying authenticity (use of unfettered speech versus strategic impression management). These behavioral signals partially mediated the relation between candidate preferences and authenticity judgments. Moreover, voters, given their partisan preferences, differentially weighted candidates' use of unfettered speech and strategic impression management tactics in their judgments of authenticity. Finally, unfiltered/politically incorrect speech was found to have both positive and negative effects on authenticity judgments. Findings further elucidate the nature of authenticity as perceived in others and identify intermediary variables and boundary conditions that influence those perceptions.     

Naïve and Robust: Class‐Conditional Independence in Human Classification Learning

Humans excel in categorization. Yet from a computational standpoint, learning a novel probabilistic classification task involves severe computational challenges. The present paper investigates one way to address these challenges: assuming class‐conditional independence of features. This feature independence assumption simplifies the inference problem, allows for informed inferences about novel feature combinations, and performs robustly across different statistical environments. We designed a new Bayesian classification learning model (the dependence‐independence structure and category learning model, DISC‐LM) that incorporates varying degrees of prior belief in class‐conditional independence, learns whether or not independence holds, and adapts its behavior accordingly. Theoretical results from two simulation studies demonstrate that classification behavior can appear to start simple, yet adapt effectively to unexpected task structures. Two experiments—designed using optimal experimental design principles—were conducted with human learners. Classification decisions of the majority of participants were best accounted for by a version of the model with very high initial prior belief in class‐conditional independence, before adapting to the true environmental structure. Class‐conditional independence may be a strong and useful default assumption in category learning tasks.     

Integrating Fast and Frugal Heuristics with a Model of Memory‐based Cue Generation

Although the fast and frugal heuristics have been studied extensively, relatively little attention has been paid to how cues are generated to be used within the heuristics. The goal of this paper is to propose and test a memory‐based model of how cues are generated and used in cue‐based inferences. The current study advances theory by integrating the fast and frugal heuristics with HyGene, a memory‐based model of how decision makers generate and evaluate hypotheses. Using archival data in which memory retrieval variables were not directly manipulated, we demonstrate that participants' cue selection behavior is consistent with memory‐based retrieval. Further, by directly manipulating memory retrieval within a cue‐based stock‐forecasting task, we demonstrate that memory processes underlie cue use. Participants' cue use varied depending on the relationship between cue validity and the frequency with which the cues were seen during learning. The HyGene model provided the best account of the empirical data, providing further evidence for the critical role of memory in judgment and decision making. Copyright © 2018 John Wiley & Sons, Ltd.     

Of BOLD Claims and Excessive Fears: A Call for Caution and Patience Regarding Political Neuroscience

Published and informal assessments of the prospects for neuroimaging in political science have tended to range from overexuberant to reflexively dismissive. We seek to present a cautious but fair middle ground in considering this new methodology, primarily from an epistemological perspective. Our examination centers on the relationship between two levels of analysis, focusing on the potential for connection between behavior‐based theories of political psychology and cognition and the neural processes and systems involved in generating behaviors and states of mind. We explore the place of each level of analysis on its own, as well as the potential for the fruitful interaction of the two. This analysis brings together opinions and ideas presented by others in various forums and across multiple disciplines, offers a discussion of the the promises and perils of neuroimaging in its application to social science, as well as some practical thoughts regarding its early‐stage incorporation into political psychology. We argue in favor of proceeding with more substantial incorporation of neuroimaging into political psychology's methodological arsenal, but note that this will initially require both (1) greater acceptance of work more focused on presenting empirical results than on providing dispositive evidence in broader theoretical debates and (2) a commitment on the part of those conducting this research to refrain from overstating the definitiveness of its theoretical implications.     

Cheapened altruism: Discounting personally affected prosocial actors

Are charitable donors always perceived as charitable? Three studies suggest that although having a personal connection to a cause motivates much charitable giving, donors who have been personally affected by the target cause are given less “credit” for their donations, i.e., are perceived as less intrinsically charitable. These donors are perceived as having selfish motivations even when they have nothing economic or social to gain from the donation. More specifically, personally-affected donors are perceived as driven by emotional selfishness, or a desire to improve their own hedonic state rather a desire to improve the welfare of others, which lessens the charitable credit that they receive. In addition, although donors who have been personally affected by the target cause are seen as less charitable, they are perceived more favorably in other ways (e.g., more loyal).     

Grammatical gender and inferences about biological properties in german-speaking children

In German, nouns are assigned to one of the three gender classes. For most animal names, however, the assignment is independent of the referent's biological sex. We examined whether German-speaking children understand this independence of grammar from semantics or whether they assume that grammatical gender is mapped onto biological sex when drawing inferences about sex-specific biological properties of animals. Two cross-linguistic studies comparing German-speaking and Japanese-speaking preschoolers were conducted. The results suggest that German-speaking children utilize grammatical gender as a cue for inferences about sex-specific properties of animals. Further, we found that Japanese- and German-speaking children recruit different resources when drawing inferences about sex-specific properties: Whereas Japanese children paralleled their pattern of inference about properties common to all animals, German children relied on the grammatical gender class of the animal. Implications of these findings for studying the relation between language and thought are discussed.     

Generic language use reveals domain differences in young children's expectations about animal and artifact categories

The goal of the present study was to explore domain differences in young children's expectations about the structure of animal and artifact categories. We examined 5-year-olds’ and adults’ use of category-referring generic noun phrases (e.g., “Birds fly”) about novel animals and artifacts. The same stimuli served as both animals and artifacts; thus, stimuli were perceptually identical across domains, and domain was indicated exclusively by language. Results revealed systematic domain differences: children and adults produced more generic utterances when items were described as animals than artifacts. Because the stimuli were novel and lacking perceptual cues to domain, these findings must be attributed to higher-order expectations about animal and artifact categories. Overall, results indicate that by age 5, children are able to make knowledge-based domain distinctions between animals and artifacts that may be rooted in beliefs about the coherence and homogeneity of categories within these domains.     

An Eye‐Tracking Study of Exploitations of Spatial Constraints in Diagrammatic Reasoning

Semantic studies on diagrammatic notations (Barwise & Etchemendy, 1990 ; Shimojima, 1995 ; Stenning & Lemon, 2001 ) have revealed that the “non‐deductive,” “emergent,” or “perceptual” effects of diagrams (Chandrasekaran, Kurup, Banerjee, Josephson, & Winkler, 2004 ; Kulpa, 2003 ; Larkin & Simon, 1987 ; Lindsay, 1988 ) are all rooted in the exploitation of spatial constraints on graphical structures. Thus, theoretically, this process is a key factor in inference with diagrams, explaining the frequently observed reduction of inferential load. The purpose of this study was to examine the empirical basis for this theoretical suggestion, focusing on the reality of the constraint‐exploitation strategy in actual practices of diagrammatic reasoning. Eye movements were recorded while participants used simple position diagrams to solve three‐ or four‐term transitive inference problems. Our experiments revealed that the participants could exploit spatial constraints on graphical structures even when (a) they were not in the position of actually manipulating diagrams, (b) the semantic rule for the provided diagrams did not match their preferences, and (c) the constraint‐exploitation strategy invited a partly adverse effect. These findings indicate that the hypothesized process is in fact robust, with the potential to broadly account for the inferential advantage of diagrams.     

Reversing the Counterfactual Analysis of Causation

The counterfactual analysis of causation has focused on one particular counterfactual conditional, taking as its starting‐point the suggestion that C causes E iff (～C □→ ～E). In this paper, some consequences are explored of reversing this counterfactual, and developing an account starting with the idea that C causes E iff (～E □→ ～C). This suggestion is discussed in relation to the problem of pre‐emption. It is found that the ‘reversed’ counterfactual analysis can handle even the most difficult cases of pre‐emption with only minimal complications. The paper closes with a discussion of the wider philosophical implications of developing a reversed counterfactual analysis, especially concerning the differentiation of causes from causal conditions, causation by absences, and the extent to which causes suffice for their effects.