Bayesian analysis of mixtures in structural equation models with non‐ignorable missing data

Structural equation models (SEMs) have become widely used to determine the interrelationships between latent and observed variables in social, psychological, and behavioural sciences. As heterogeneous data are very common in practical research in these fields, the analysis of mixture models has received a lot of attention in the literature. An important issue in the analysis of mixture SEMs is the presence of missing data, in particular of data missing with a non‐ignorable mechanism. However, only a limited amount of work has been done in analysing mixture SEMs with non‐ignorable missing data. The main objective of this paper is to develop a Bayesian approach for analysing mixture SEMs with an unknown number of components and non‐ignorable missing data. A simulation study shows that Bayesian estimates obtained by the proposed Markov chain Monte Carlo methods are accurate and the Bayes factor computed via a path sampling procedure is useful for identifying the correct number of components, selecting an appropriate missingness mechanism, and investigating various effects of latent variables in the mixture SEMs. A real data set on a study of job satisfaction is used to demonstrate the methodology.     

Development and validation of a Coping with Discrimination Scale: factor structure, reliability, and validity

Four studies were conducted to develop and validate the Coping With Discrimination Scale (CDS). In Study 1, an exploratory factor analysis (N = 328) identified 5 factors: Education/Advocacy, Internalization, Drug and Alcohol Use, Resistance, and Detachment, with internal consistency reliability estimates ranging from .72 to .90. In Study 2, a confirmatory factor analysis (N = 328) provided cross-validation of the 5-factor model as well as evidence for validity of the scale. The validity evidence was similar across racial groups and for males and females. In Study 3, the estimated 2-week test-retest reliabilities (N = 53) were between .48 and .85 for the 5 factors. Education/Advocacy, Internalization, Drug and Alcohol Use, and Detachment were positively associated with active coping, self-blame, substance use, and behavioral disengagement, respectively, providing further support for validity of the CDS. Finally, incremental validity evidence was obtained in Study 4 (N = 220), where it was shown that the CDS explained variance in outcome variables (i.e., depression, life satisfaction, self-esteem, and ethnic identity) that could not be explained by general coping strategies.     

Determinants of Standard Errors of MLEs in Confirmatory Factor Analysis

This paper studies changes of standard errors (SE) of the normal-distribution-based maximum likelihood estimates (MLE) for confirmatory factor models as model parameters vary. Using logical analysis, simplified formulas and numerical verification, monotonic relationships between SEs and factor loadings as well as unique variances are found. Conditions under which monotonic relationships do not exist are also identified. Such functional relationships allow researchers to better understand the problem when significant factor loading estimates are expected but not obtained, and vice versa. What will affect the likelihood for Heywood cases (negative unique variance estimates) is also explicit through these relationships. Empirical findings in the literature are discussed using the obtained results.     

利用脑成像多体素模式分析解码认知的神经表征:原理和应用

多体素模式分析(multi-voxel pattern analysis,MVPA)是一种基于机器学习理论发展出来的新的功能磁共振数据分析技术。MVPA技术通过训练分类器,对由不同认知状态引起的多体素信号模式进行分类。与传统的基于单个体素的分析方法相比,该技术可更敏感地检测脑对认知状态的表征,并使得从神经信号解码认知状态成为可能。文章介绍MVPA技术的基本原理、分析步骤以及可以用MVPA来解决的科学问题,并对应用中可能面临的问题提供了参考建议。     

大学生对心理健康必备能力的认知

本研究以200名大学生为被试,以访谈及问卷的方式对大学生心理健康必备能力的认知进行了调查研究,并建立了大学生心理健康必备能力认知结构模型,结果表明:大学生所认知的自己心理健康必备能力由自我调控、社会应对、学习和人际交往这四个方面的能力组成,它们彼此独立,但又相互关联。     

Application of the stagnant stage concept for monitoring Mn partitioning at the austenite-ferrite interface in the intercritical region for Fe–Mn–C alloys

The length of the stagnant stage during the new ferrite growth starting from a mixture of austenite and ferrite has been investigated for a Fe-0.17Mn-0.023C (wt%) alloy. It was found that the stagnant stage depends on the thermal path followed to create the mixture, and deduce that the tie-lines for austenite to ferrite transformation are quite different from those for ferrite to austenite transformation. The length of the stagnant stage is determined by the very local partitioning effect at the interface, and it can be used as a tool to monitor the Mn partitioning.     

Detrimental effect of cellular precipitation on the creep strength of Inconel740H

Cellular precipitation (also known as discontinuous precipitation) has been observed at the grain boundaries of a newly developed nickel-based Inconel740H alloy designed for use at 700?°C in advanced ultrasupercritical coal-fired power plants. By means of element mapping and selected area diffraction, the cellular precipitates were identified as Cr-rich M₂₃C₆ carbides. The onset of cellular precipitation was found to follow a pucker mechanism in Inconel740H. The cellular precipitates at the grain boundaries, even at low volume fractions, were severely detrimental to the creep strength at 750?°C. The creep rupture life of Inconel740H containing cellular precipitates at grain boundaries was only one-tenth of that for the alloy without cellular precipitates. The reason for the drastically decreased creep rupture life is attributed to the poor resistance of cellular precipitates to crack propagation during creep.     

关注肿瘤患者避免过度诊疗——解析ASCO大会关于肿瘤诊疗的5项建议

现代肿瘤的诊疗水平已经有了长足的进步,先进的诊断技术使得很多肿瘤得以早期发现并积极治疗,很多晚期患者也不再面临无药可用的境地,但由于临床医生的认识存在偏差,存在过度诊断和过度治疗的问题,进而给患者带来不必要的负担和痛苦。美国临床肿瘤学会（ASC0）年会上发布了一篇名为“ASCO为改善肿瘤治疗质量及医疗花费的5项建议”的文章,特别提出要重视五项临床广泛应用、花费较大,但缺乏高级临床证据的肿瘤治疗或干预措施,也提示我们需要充分评估,综合思考,为合适的患者提供正确的诊治方案,才能给患者带来更大的获益。     

转化医学模式对临床医学八年制教学改革的启示

近年来我国部分重点医学院校陆续推出精英教育培养模式,以八年制医学生的培养为代表.临床医学八年制的培养更需要基础医学与临床医学之间相互整合,是完善“八年一贯,本博融通”培养模式的关键.转化医学的出现,为消除基础与临床的屏障,提高八年制医学生基础医学研究水平,加强临床思维培养提供了新的平台和途径.