Evaluating expectations about negative emotional states of aggressive boys using Bayesian model selection

Researchers often have expectations about the research outcomes in regard to inequality constraints between, e.g., group means. Consider the example of researchers who investigated the effects of inducing a negative emotional state in aggressive boys. It was expected that highly aggressive boys would, on average, score higher on aggressive responses toward other peers than moderately aggressive boys, who would in turn score higher than nonaggressive boys. In most cases, null hypothesis testing is used to evaluate such hypotheses. We show, however, that hypotheses formulated using inequality constraints between the group means are generally not evaluated properly. The wrong hypotheses are tested, i.e.. the null hypothesis that group means are equal. In this article, we propose an innovative solution to these above-mentioned issues using Bayesian model selection, which we illustrate using a case study.     

Model inference or model selection: discussion of Klugkist, Laudy, and Hoijtink (2005)

I. Klugkist, O. Laudy, and H. Hoijtink (2005) presented a Bayesian approach to analysis of variance models with inequality constraints. Constraints may play 2 distinct roles in data analysis. They may represent prior information that allows more precise inferences regarding parameter values, or they may describe a theory to be judged against the data. In the latter case, the authors emphasized the use of Bayes factors and posterior model probabilities to select the best theory. One difficulty is that interpretation of the posterior model probabilities depends on which other theories are included in the comparison. The posterior distribution of the parameters under an unconstrained model allows one to quantify the support provided by the data for inequality constraints without requiring the model selection framework.     

L’intensification du travail,et l’intensification des changements dans le travail : quels enjeux pour les travailleurs expérimentés ?

In this article we address, on the basis of various knowledge in ergonomics, work psychology and work demography, the stakes of a confrontation between two trends in progress: on one side the structural ageing of workforce, on the other side work intensification, and intensification of changes at work. This analyze includes statements on these evolutions by themselves, and a synthesis of knowledge on the difficulties created by the intensification of work, or changes at work, for elderly workers, but also on work strategies that those can elaborate, using their experience, in order to cope with these constraints.     

Estimation of covariance structure models with parameters subject to functional restraints

This paper demonstrates the feasibility of using the penalty function method to estimate parameters that are subject to a set of functional constraints in covariance structure analysis. Both types of inequality and equality constraints are studied. The approaches of maximum likelihood and generalized least squares estimation are considered. A modified Scoring algorithm and a modified Gauss-Newton algorithm are implemented to produce the appropriate constrained estimates. The methodology is illustrated by its applications to Heywood cases in confirmatory factor analysis, quasi-Weiner simplex model, and multitrait-multimethod matrix analysis.The author is indebted to several anonymous reviewers for creative suggestions for improvement of this paper. Computer funding is provided by the Computer Services Centre, The Chinese University of Hong Kong.     

Bayes factors for testing inequality constrained hypotheses: Issues with prior specification

Several issues are discussed when testing inequality constrained hypotheses using a Bayesian approach. First, the complexity (or size) of the inequality constrained parameter spaces can be ignored. This is the case when using the posterior probability that the inequality constraints of a hypothesis hold, Bayes factors based on non‐informative improper priors, and partial Bayes factors based on posterior priors. Second, the Bayes factor may not be invariant for linear one‐to‐one transformations of the data. This can be observed when using balanced priors which are centred on the boundary of the constrained parameter space with a diagonal covariance structure. Third, the information paradox can be observed. When testing inequality constrained hypotheses, the information paradox occurs when the Bayes factor of an inequality constrained hypothesis against its complement converges to a constant as the evidence for the first hypothesis accumulates while keeping the sample size fixed. This paradox occurs when using Zellner's g prior as a result of too much prior shrinkage. Therefore, two new methods are proposed that avoid these issues. First, partial Bayes factors are proposed based on transformed minimal training samples. These training samples result in posterior priors that are centred on the boundary of the constrained parameter space with the same covariance structure as in the sample. Second, a g prior approach is proposed by letting g go to infinity. This is possible because the Jeffreys–Lindley paradox is not an issue when testing inequality constrained hypotheses. A simulation study indicated that the Bayes factor based on this g prior approach converges fastest to the true inequality constrained hypothesis.     

EFFECT OF STRUCTURAL CUEING AND DECISION TYPE FOR IMPROVING RETENTION OF TECHNICAL TEXT

This study investigated the effects of structural cueing (color or no color) and decision level (rote or semantic) on students' verbatim retention of technical prose. Structural cueing represented the assimilation of encoding hypothesis for improving memory, and decision tasks represented the distinctiveness of encoding hypothesis for promoting deep processing. Subjects read an article on a microcomputer monitor in which either color‐coding or white‐only print was used to represent the structural importance among ideas in each paragraph and then, subsequent to each paragraph, responded to either rote memory or semantic memory decision statements. Results of a free written recall measure using a two‐factor analysis of covariance, revealed significant differences between students' retention on decision type but no differences based on color cueing. That is, students who responded to semantic level decision statements recalled more of the text than those who responded to the rote level decision statements. The results supported the distinctiveness of encoding hypothesis for learning via the microcomputer but did not support the assimilation of encoding hypothesis.     

Likelihood inference on the underlying structure of IRT models

The assumptions underlying item response theory (IRT) models may be expressed as a set of equality and inequality constraints on the parameters of a latent class model. It is well known that the same assumptions imply that the parameters of the manifest distribution have to satisfy a more complicated set of inequality constraints which, however, are necessary but not sufficient. In this paper, we describe how the theory for likelihood-based inference under equality and inequality constraints may be used to test the underlying assumptions of IRT models. It turns out that the analysis based directly on the latent structure is simpler and more flexible. In particular, we indicate how several interesting extensions of the Rasch model may be obtained by partial relaxation of the basic constraints. An application to a data set provided by Educational Testing Service is used to illustrate the approach.We thank Dr. Gorman and Dr. Rogers of the Educational Testing Service for providing the data analyzed in Section 4. We also thank three reviewers for comments and suggestions.This revised article was published online in August 2005 with the PDF paginated correctly.     

Empirical evaluation and justification of methodologies in psychological science.

The purpose of this article is to describe a relatively new movement in the history and philosophy of science, naturalism, a form of pragmatism emphasizing that methodological principles are empirical statements. Thus, methodological principles must be evaluated and justified on the same basis as other empirical statements. On this view, methodological statements may be less secure than the specific scientific theories to which they give rise. The authors examined the feasibility of a naturalistic approach to methodology using logical and historical analysis and by contrasting theories that predict new facts versus theories that explain already known facts. They provide examples of how differences over methodological issues in psychology and in science generally may be resolved using a naturalistic, or empirical, approach.     

A Test of Order-Constrained Hypotheses for Circular Data With Applications to Human Movement Science

Researchers studying the movements of the human body often encounter data measured in angles (e.g., angular displacements of joints). The evaluation of these circular data requires special statistical methods. The authors introduce a new test for the analysis of order-constrained hypotheses for circular data. Through this test, researchers can evaluate their expectations regarding the outcome of an experiment directly by representing their ideas in the form of a hypothesis containing inequality constraints. The resulting data analysis is generally more powerful than one using standard null hypothesis testing. Two examples of circular data from human movement science are presented to illustrate the use of the test. Results from a simulation study show that the test performs well.     

Scientific knowledge suppresses but does not supplant earlier intuitions

When students learn scientific theories that conflict with their earlier, naïve theories, what happens to the earlier theories? Are they overwritten or merely suppressed? We investigated this question by devising and implementing a novel speeded-reasoning task. Adults with many years of science education verified two types of statements as quickly as possible: statements whose truth value was the same across both naïve and scientific theories of a particular phenomenon (e.g., “The moon revolves around the Earth”) and statements involving the same conceptual relations but whose truth value differed across those theories (e.g., “The Earth revolves around the sun”). Participants verified the latter significantly more slowly and less accurately than the former across 10 domains of knowledge (astronomy, evolution, fractions, genetics, germs, matter, mechanics, physiology, thermodynamics, and waves), suggesting that naïve theories survive the acquisition of a mutually incompatible scientific theory, coexisting with that theory for many years to follow.     

Differences in Aggression,Attitudes Toward Women,and Distrust as Reflected in Popular Music Preferences

This article examines the complex relationship between dispositions, popular music preferences, and attitudes. In accordance with selective-exposure and excitation-transfer theories, it was expected that anger and self-esteem dispositions would influence popular-music preferences and attitudinal differences. Using a sample of 243 persons, we examined hypotheses and research questions seeking to link music preferences with three attitudes: aggression, attitudes toward women, and trust/distrust. Anger and self-esteem were treated as covariates. Multivariate analysis of covariance showed significant attitudinal differences among those who preferred different music genres. As compared with most other genres, heavy-metal music listeners exhibited more aggression and lesser regard for women, and rap listeners showed more aggression and distrust. Implications of these findings were discussed.     

Bayesian estimation and model selection in ordered latent class models for polytomous items

In a latent class IRT model in which the latent classes are ordered on one dimension, the class specific response probabilities are subject to inequality constraints. The number of these inequality constraints increase dramatically with the number of response categories per item, if assumptions like monotonicity or double monotonicity of the cumulative category response functions are postulated. A Markov chain Monte Carlo method, the Gibbs sampler, can sample from the multivariate posterior distribution of the parameters under the constraints. Bayesian model selection can be done by posterior predictive checks and Bayes factors. A simulation study is done to evaluate results of the application of these methods to ordered latent class models in three realistic situations. Also, an example of the presented methods is given for existing data with polytomous items. It can be concluded that the Bayesian estimation procedure can handle the inequality constraints on the parameters very well. However, the application of Bayesian model selection methods requires more research.     

社会不平等如何影响低地位者的系统合理信念

系统合理信念反映了人们的系统支持态度,即对社会系统公正性、合理性、正当性的感知,以及相应的支持和维护社会系统的态度。以往关于社会不平等与低地位者系统合理信念的关系形成了两种对立的理论观点。一方面,社会认同理论等自利取向的理论认为,严重的不平等不利于低地位者维护自我及内群体利益,因此会损害其系统合理信念;另一方面,系统合理化理论却提出,在不平等更极端（而非平等）的社会中,人们（甚至是低地位者）反而更可能合理化不平等,表现出更高的系统合理信念。实证研究中,两种观点分别得到了一些研究的支持,但同时也面临很多质疑。 面对上述分歧,本文提出了一个整合性的解释框架,即“社会不平等影响低地位者系统合理信念的双路径模型”。该模型认为,自利取向理论与系统合理化理论其实并不矛盾,而是共同解释了不平等与低地位者系统合理信念关系的“全貌”。因此,理论争议的焦点不在于不平等究竟增强还是减弱低地位者的系统合理信念,而在于分析不平等增强或减弱低地位者系统合理信念的不同条件（即认知基础）及其内在机制（即动机基础）。 第一,在认知基础方面,不同于以往研究仅关注不平等“量”的程度及其与系统合理信念的线性关系,该模型认为还应关注不平等“质”的差异及其不同效应,即关注低地位者对不平等的认知过程。一方面,严重的不平等损害低地位者个人或群体的现实利益,构成一种现实威胁;另一方面,严重不平等的社会现状与人们关于社会系统公正性、合理性的信念相冲突,构成一种象征威胁。 第二,在动机基础方面,低地位者的自利动机与系统合理化动机分别使其反对或维护不平等现状,且两种动机彼此冲突;不同于以往研究采用对立视角考察两种动机,或是过于强调二者之一的作用;该模型认为,两种动机是并存的,相互之间并非全或无的关系。因此有必要厘清二者发挥作用的条件,即什么影响二者孰强孰弱,又是什么决定了何者发挥主导作用。 第三,区分不平等“质”的差异是厘清自利动机与系统合理化动机如何发挥作用的关键。换言之,不同动机为低地位者反对或维护不平等现状提供了动力,而何种动机发挥主导作用则取决于低地位者如何对不平等进行认知。具体而言,当凸显不平等在个体或群体水平的现实威胁时,更可能激活低地位者的自利动机（进而抑制其系统合理化动机）,继而损害其系统合理信念;而当凸显不平等在系统水平的象征威胁时,更可能激活其系统合理化动机（进而抑制其自利动机）,继而增强其系统合理信念。 “双路径模型”通过分析不平等影响低地位者系统合理信念的不同认知基础,进而厘清不同动机的作用,将以往研究中看似矛盾的结论整合于一,为理解不平等对低地位者系统合理信念的影响、解释两种理论的“分歧”提供了一种整合框架,需要未来研究进一步检验和发展。     

Reference, paradoxes and truth

We introduce a variant of pointer structures with denotational semantics and show its equivalence to systems of boolean equations: both have the same solutions. Taking paradoxes to be statements represented by systems of equations (or pointer structures) having no solutions, we thus obtain two alternative means of deciding paradoxical character of statements, one of which is the standard theory of solving boolean equations. To analyze more adequately statements involving semantic predicates, we extend propositional logic with the assertion operator and give its complete axiomatization. This logic is a sub-logic of statements in which the semantic predicates become internalized (for instance, counterparts of Tarski’s definitions and T-schemata become tautologies). Examples of analysis of self-referential paradoxes are given and the approach is compared to the alternative ones.     

Rational Thought And Rational Behavior: A Review Of Bounded Rationality: The Adaptive Toolbox.

Standard economic theory says that the rational approach to a decision is to weigh all alternatives on all relevant dimensions and then to select the one with the highest weight. Such a procedure would maximize subjective expected utility. But, because of constraints on time and available information, people and other animals often bypass this process by using “fast and frugal” heuristics to make decisions. Rationality is thus said to be “bounded” by time and information constraints. The articles in this book describe and organize common heuristics. They show that use of such heuristics is generally the best approach to many real world problems and therefore not irrational. Heuristics evolved, they say, not as deviations from rationality but as aids to rationality in cases where the standard model would have proved to be too slow or inefficient. Although the approach of almost all of the authors of these papers is that of cognitive psychology—a focus on internal cognitive mechanisms—their findings and even their theories may be interpreted in terms of reinforcement and punishment acting on behavioral patterns.     

Initial judgment task and delay of the final validity-rating task moderate the truth effect

Repeatedly seen or heard statements are typically judged to be more valid than statements one has never encountered before. This phenomenon has been referred to as the truth effect. We conducted two experiments to assess the plasticity of the truth effect under different contextual conditions. Surprisingly, we did not find a truth effect in the typical judgment design when using a ten minutes interval between statement repetitions. However, we replicated the truth effect when changing the judgment task at initial statement exposure or when using an interval of one week rather than ten minutes. Because none of the current truth effect theories can fully account for these context effects, we conclude that the cognitive processes underlying truth judgments are more complex than has hitherto been assumed. To close the theoretical gap, we propose a revised fluency attribution hypothesis as a possible explanation of our findings.     

The Specific Analysis of Structural Equation Models

Conventional structural equation modeling fits a covariance structure implied by the equations of the model. This treatment of the model often gives misleading results because overall goodness of fit tests do not focus on the specific constraints implied by the model. An alternative treatment arising from Pearl's directed acyclic graph theory checks identifiability and lists and tests the implied constraints. This approach is complete for Markov models, but has remained incomplete for models with correlated disturbances. Some new algebraic results overcome the limitations of DAG theory and give a specific form of structural equation analysis that checks identifiability, tests the implied constraints, equation by equation, and gives consistent estimators of the parameters in closed form from the equations. At present the method is limited to recursive models subject to exclusion conditions. With further work, specific structural equation modeling may yield a complete alternative to the present, rather unsatisfactory, global covariance structure analysis.     

A Newton procedure for conditionally linear mixed-effects models

This article reviews Newton procedures for the analysis of mean and covariance structures that may be functions of parameters that enter a model nonlinearly. The kind of model considered is a mixed-effects model that is conditionally linear with regard to its parameters. This means parameters entering the model nonlinearly must be fixed, whereas those entering linearly may vary across individuals. This framework encompasses several models, including hierarchical linear models, linear and nonlinear factor analysis models, and nonlinear latent curve models. A full maximum-likelihood estimation procedure is described. Mx, a statistical software package often used to estimate structural equation models, is considered for estimation of these models. An example with Mx syntax is provided.