Heterogeneous factor analysis models: A bayesian approach

Multilevel factor analysis models are widely used in the social sciences to account for heterogeneity in mean structures. In this paper we extend previous work on multilevel models to account for general forms of heterogeneity in confirmatory factor analysis models. We specify various models of mean and covariance heterogeneity in confirmatory factor analysis and develop Markov Chain Monte Carlo (MCMC) procedures to perform Bayesian inference, model checking, and model comparison.We test our methodology using synthetic data and data from a consumption emotion study. The results from synthetic data show that our Bayesian model perform well in recovering the true parameters and selecting the appropriate model. More importantly, the results clearly illustrate the consequences of ignoring heterogeneity. Specifically, we find that ignoring heterogeneity can lead to sign reversals of the factor covariances, inflation of factor variances and underappreciation of uncertainty in parameter estimates. The results from the emotion study show that subjects vary both in means and covariances. Thus traditional psychometric methods cannot fully capture the heterogeneity in our data.     

Virtual reality and the new psychophysics

Virtual reality (VR) promises methodological rigour with the extra benefit of allowing us to study the context-dependent behaviour of individuals in their natural environment. Pan and Hamilton (2018, Br. J. Psychol.) provide a useful overview of methodological recommendations for using VR. Here, we highlight some other aspects of the use of VR. Our first argument is that VR can be useful by virtue of its differences from the normal perceptual environment. That is, by virtue of its relative non-realism and poverty of its perceptual elements, it can actually offer increased clarity with respect to the features of interest for the researcher. Our second argument is that VR exerts its measurable influence more by eliciting an acceptance of the virtual world (i.e., ‘suspension of disbelief’) rather than by eliciting a true belief of the realism of the VR environment. We conclude by providing a novel suggestion for combining neuroimaging methods with embodied VR that relies on the suspension of disbelief.     

Examining arguments against quantitative research: “Case studies” illustrating the challenge of finding a sound philosophical basis for a human sciences approach to psychology

This article offers a close examination of critiques of quantitative research by Michell, 2011, Marecek, 2011, and Morawski (2011). One goal is to show that these three critics actually share with most mainstream quantitative researchers commitments to the Cartesian framework, even though this is not obvious because Cartesianism can appear in different guises. As a result of these commitments, the three theorists advance criticisms of mainstream quantitative research that fail to identify its key failings, put forward flawed views about how we should conduct research, and offer misguided criticisms of an approach I advocate called explicitly interpretive quantitative research. Another goal is to use the examination of the three critiques as a vehicle for clarifying the participatory perspective, a philosophical viewpoint that departs from the Cartesian framework. With regard to research methodology, the participatory perspective provides the basis for explicitly interpretive quantitative research, leads to ideas about changes we should make in how we conduct qualitative research, and treats quantitative and qualitative research as fundamentally similar because both should be pursued as interpretive modes of inquiry. I suggest that my analyses of the three critiques of quantitative research – or “case studies,” as I call these analyses – also may prove useful to researchers and theorists who want to develop a human sciences approach to other issues besides research methodology by helping them (1) recognize when lines of thinking that seem to depart from the mainstream actually represent variants of Cartesianism, and (2) consider what the participatory perspective might have to offer if they were to use it as the philosophical basis for their efforts.     

Algorithmic Proof Methods and Cut Elimination for Implicational Logics Part I: Modal Implication

In this work we develop goal-directed deduction methods for the implicational fragment of several modal logics. We give sound and complete procedures for strict implication of K, T, K4, S4, K5, K45, KB, KTB, S5, G and for some intuitionistic variants. In order to achieve a uniform and concise presentation, we first develop our methods in the framework of Labelled Deductive Systems [Gabbay 96]. The proof systems we present are strongly analytical and satisfy a basic property of cut admissibility. We then show that for most of the systems under consideration the labelling mechanism can be avoided by choosing an appropriate way of structuring theories. One peculiar feature of our proof systems is the use of restart rules which allow to re-ask the original goal of a deduction. In case of K, K4, S4 and G, we can eliminate such a rule, without loosing completeness. In all the other cases, by dropping such a rule, we get an intuitionistic variant of each system. The present results are part of a larger project of a goal directed proof theory for non-classical logics; the purpose of this project is to show that most implicational logics stem from slight variations of a unique deduction method, and from different ways of structuring theories. Moreover, the proof systems we present follow the logic programming style of deduction and seem promising for proof search [Gabbay and Reyle 84, Miller et al. 91].     

Process, Content, and Feminist Reflexivity: One Researcher's Exploration

This article explores the unraveling of the relationship between research methodology, process, and content as revealed through my own feminist research project. I examine the evolution of my research process with one participant from a larger study, as I sought to better understand a story she told about racism. First, I address the theoretical underpinnings of feminist reflexivity and research, which challenge traditional paradigms. Next, I present the participant's (a white family day care provider's) story about racism in her practice which was revealed during an interview process. Subsequently, I present a second dialogue around the story in which we (researcher and participant) later engaged. In the process, I analyze my struggles, as a researcher trained in positivist methods, to engage in reflexive research methods. Finally, I evaluate the gains made for me as a researcher in the process and content of research conducted with a feminist reflexive frame and suggest their utility in deconstructing White racism.     

Moving in Parallel Toward a Modern Modeling Epistemology: Bayes Factors and Frequentist Modeling Methods

The Bayesian-frequentist debate typically portrays these statistical perspectives as opposing views. However, both Bayesian and frequentist statisticians have expanded their epistemological basis away from a singular focus on the null hypothesis, to a broader perspective involving the development and comparison of competing statistical/mathematical models. For frequentists, statistical developments such as structural equation modeling and multilevel modeling have facilitated this transition. For Bayesians, the Bayes factor has facilitated this transition. The Bayes factor is treated in articles within this issue of Multivariate Behavioral Research. The current presentation provides brief commentary on those articles and more extended discussion of the transition toward a modern modeling epistemology. In certain respects, Bayesians and frequentists share common goals.     

Shoppers in the Spiritual Supermarket: A Quantitative Study of Visitors to Scandinavia’s Largest Alternative Fair

Presenting data from a quantitative survey (N=362) at ‘The Great Alternative Fair’ in Lillestrøm, Norway, this article explores the demographic and religious profiles of the ‘customers’ in the ‘spiritual marketplace’. Many adhere to ideas that are historically associated with different religious traditions. At the same time, there are strong positive statistical correlations between belief in alternative ideas, such as healing, reincarnation, channelling, and clairvoyance. This indicates that such ideas constitute a clustered and shared set of beliefs. Against this background, the article questions the widely held assumption that people who are oriented towards alternative spiritualities are independent of institutions and authorities and it argues that they are informed to a large extent by a set of collective resources. It is suggested that the marketplace, which constitutes a common framework of interaction, plays a key role in connecting various ideas and actors and in creating a common ideological profile.     

Too individualistic for safety culture? Non-traffic related work safety among heavy goods vehicle drivers

IntroductionThis article reports on a study of non-traffic related work safety among drivers of heavy goods vehicles in Denmark. In the heavy goods vehicle transport (HGV) sector only 6.4% of workplace accidents involving drivers are traffic related. HGV work is characterised by solitary work, as drivers tend to work at a physical distance from their own company and their working environment is also influenced by the working environment of other companies e.g. the places where they deliver goods. This study focuses on an analysis of HGV drivers’ and managers’ differentiated understandings of risk and safety and its management within an organisational context. The situational focus involves viewing HGV drivers’ working environment as a part of the organisational structure as well as of other social relationships. An understanding of safety culture as practice is applied with the view of identifying values and attitudes as well as organisational and technical aspects in relation to how individualist or collectivist understandings of risk and safety influence the working environment in HGVs.MethodThe study applied a mixed methods approach and in this article the qualitative interviews conducted with drivers and managers is the primary data source.ResultsThis study suggests a widespread understanding of drivers as being individually oriented in their work, from drivers and management alike. However, the study also demonstrates that, in conducting their work, the drivers are actually interdependent, and share knowledge frequently, albeit informally. The organisational structure of the company shapes their individual attitudes towards safety but they also report being dependent on relationships with, and information from, their fellow colleagues, former colleagues and friends who shape their understandings and attitudes towards hazards and safety practices. The analysis points to risk-taking and unsafe practices as prevalent among HGV drivers, who often refer to risk as trivial and the management of such risks as one’s own responsibility. Knowledge of how to manage risks in everyday practice is shown to be principally related to personal experiences but also to the good advice and examples of fellow drivers.ConclusionsThe analysis points to interdependent and collectivist practices among HGV drivers even though they are perceived as being individualistically oriented when it comes to safety. Therefore, non-traffic related safety practices, in this case the loading and unloading of vehicles, occur in the grey zone of organisational safety management. Despite the fact that organisational safety initiatives are initiated, the management sees limited possibilities for enforcing them and hence safety practice is often left to the individual driver.Practical applicationsA safety culture perspective might enhance work safety among HGV drivers if we are able to understand workplace culture in a pluralistic way. Collectivist practice among the drivers can be utilised in order to improve knowledge sharing and situational safety practices. The informal communication identified among the drivers might offer a new model for safety initiatives based on more collectivist, albeit informal, safety culture practices on behalf of HGV companies.     

Health behaviour change theory meets falls prevention: Feasibility of a habit-based balance and strength exercise intervention for older adults

ObjectivesHabit formation is a proposed mechanism for behaviour maintenance. Very few falls prevention studies have adopted this as an intervention framework and outcome. Therefore, we tested feasibility of a theory-based behaviour change intervention that encouraged women to embed balance and strength exercises into daily life routines (e.g., eating, self-care routines).DesignThe EASY LiFE study was a mixed-methods, 4-month feasibility intervention that included seven group-based sessions and two telephone calls.Main outcome measuresWe obtained performance-based (i.e., Short-Physical-Performance-Battery) and psychological self-report measures (i.e., intention, self-efficacy, planning, action control, habit strength, quality of life) from 13 women at baseline (T1) and 4-month follow-up (T2). We applied the Framework-Method to post-intervention, semi-structured interviews to evaluate program content and delivery.ResultsIn total, 10 of 13 women completed the program (M_age = 66.23, SD = 3.98) and showed changes in their level of action control [mean difference_T1−T2 = 1.7, 95% CI (−2.2 to −0.8)], action planning [mean difference_T1−T2 = 0.8, 95% CI (−1.1 to −0.2)], automaticity [mean difference_T1−T2 = 2.5, 95% CI (−3.7 to −1.2)], and exercise identity [mean difference_T1−T2 = 2.0, 95% CI (−3.2 to −0.8)]. Based on the Theoretical Domains Framework we identified knowledge, behavioural regulation, and social factors as important themes. For program delivery, dominant themes were engagement, session facilitators and group format.ConclusionThe theory-based framework showed feasibility for promoting lifestyle integrated balance and strength exercise habits. Using activity and object-based cues may be particularly effective in generating action and automaticity.     

CD-MST初始阶段模块组建方法比较

具有认知诊断功能的计算机化多阶段测验(CD-MST)是CDA和MST相结合的一种测验方式。由于CD-MST自适应频次较少,初始阶段模块组建会影响整个测验的判准率。借鉴CD-CAT初始项目选取方法,根据CDA和MST自身特点,提出了7种CD-MST初始阶段模块组建方法,分别是随机法、选题策略法、R*矩阵法、CTTID法、CDI法、CTTIDR*法和CDIR*法。采用模拟研究对不同项目质量下7种方法的判准率进行了比较。研究结果表明,当初始阶段结束时,包含R*矩阵的方法判准率显著高于其他方法,尤其是CTTIDR*法;整个测验结束时,CTTIDR*法较其他方法仍然有优势,CDIR*法和R*矩阵法结果较为接近。选题策略法在初始阶段结束时判准率较低,甚至低于随机法,整个测验结束时,判准率同CDIR*法和R*矩阵法持平。4种项目质量对判准率影响较大,HD-HV题库下判准率最高,HD-LV次之,LD-HV较差,LD-LV最差。