A Bayesian Modeling Approach for Generalized Semiparametric Structural Equation Models

In behavioral, biomedical, and psychological studies, structural equation models (SEMs) have been widely used for assessing relationships between latent variables. Regression-type structural models based on parametric functions are often used for such purposes. In many applications, however, parametric SEMs are not adequate to capture subtle patterns in the functions over the entire range of the predictor variable. A different but equally important limitation of traditional parametric SEMs is that they are not designed to handle mixed data types—continuous, count, ordered, and unordered categorical. This paper develops a generalized semiparametric SEM that is able to handle mixed data types and to simultaneously model different functional relationships among latent variables. A structural equation of the proposed SEM is formulated using a series of unspecified smooth functions. The Bayesian P-splines approach and Markov chain Monte Carlo methods are developed to estimate the smooth functions and the unknown parameters. Moreover, we examine the relative benefits of semiparametric modeling over parametric modeling using a Bayesian model-comparison statistic, called the complete deviance information criterion (DIC). The performance of the developed methodology is evaluated using a simulation study. To illustrate the method, we used a data set derived from the National Longitudinal Survey of Youth.     

双语词汇理解切换中非目标语言加工

实验采用直接语音掩蔽启动范式,通过掩蔽词的有、无呈现对切换后单词的读音判断反应时产生影响,进而了解非熟练双语者双语理解切换中非目标语言加工状态。实验结果表明,无呈现掩蔽词组的反应时比有呈现组的判断反应时长;不同掩蔽词呈现时间两组中切换反应时判断不显著。实验证明无论是哪一种语言作为非目标语言,其在词汇层上均都不会被激活;双语词汇理解切换中,切换至熟练语言比切换至不熟练语言切换代价小。     

First principles study of the temperature-dependent elastic properties of W

The temperature-dependent elastic constants of body-centred cubic (bcc) phase W are presented from first principles quasi-static approach. With the quasi-harmonic approximation model, the Hugoniot equation of state and temperature-dependence linear thermal expansion coefficient is successfully obtained. The adiabatic elastic constants show a normal behaviour with temperature: decrease with increasing temperature. Based on the obtained adiabatic elastic constants, the structural stability and polycrystalline aggregate properties including bulk modulus B, shear modulus G, and B/G ratio are analysed for bcc phase W. In addition, the sound velocities as a function of temperature for bcc phase W are predicted.     

Limited‐information goodness‐of‐fit testing of diagnostic classification item response models

Despite the growing popularity of diagnostic classification models (e.g., Rupp et al., 2010, Diagnostic measurement: theory, methods, and applications, Guilford Press, New York, NY) in educational and psychological measurement, methods for testing their absolute goodness of fit to real data remain relatively underdeveloped. For tests of reasonable length and for realistic sample size, full‐information test statistics such as Pearson's X² and the likelihood ratio statistic G² suffer from sparseness in the underlying contingency table from which they are computed. Recently, limited‐information fit statistics such as Maydeu‐Olivares and Joe's (2006, Psychometrika, 71, 713) M₂ have been found to be quite useful in testing the overall goodness of fit of item response theory models. In this study, we applied Maydeu‐Olivares and Joe's (2006, Psychometrika, 71, 713) M₂ statistic to diagnostic classification models. Through a series of simulation studies, we found that M₂ is well calibrated across a wide range of diagnostic model structures and was sensitive to certain misspecifications of the item model (e.g., fitting disjunctive models to data generated according to a conjunctive model), errors in the Q‐matrix (adding or omitting paths, omitting a latent variable), and violations of local item independence due to unmodelled testlet effects. On the other hand, M₂ was largely insensitive to misspecifications in the distribution of higher‐order latent dimensions and to the specification of an extraneous attribute. To complement the analyses of the overall model goodness of fit using M₂, we investigated the utility of the Chen and Thissen (1997, J. Educ. Behav. Stat., 22, 265) local dependence statistic $X_{\mathrm{LD}}^2$ for characterizing sources of misfit, an important aspect of model appraisal often overlooked in favour of overall statements. The $X_{\mathrm{LD}}^2$ statistic was found to be slightly conservative (with Type I error rates consistently below the nominal level) but still useful in pinpointing the sources of misfit. Patterns of local dependence arising due to specific model misspecifications are illustrated. Finally, we used the M₂ and $X_{\mathrm{LD}}^2$ statistics to evaluate a diagnostic model fit to data from the Trends in Mathematics and Science Study, drawing upon analyses previously conducted by Lee et al., (2011, IJT, 11, 144).     

Cognitive control and word recognition speed influence the Stroop effect in bilinguals

Bilinguals have been shown to be less susceptible to Stroop interference in their first language than monolinguals, though the cause is currently being debated. In two experiments, we explored how cognitive control and word recognition contribute to the Stroop effect by contrasting cognitive control (via a Simon arrow task), word recognition speed (via a Chinese/English word recognition task) and Stroop susceptibility (via a verbal Stroop task) between proficient and non‐proficient Chinese–English bilinguals. Compared to non‐proficient bilinguals, proficient bilinguals showed better cognitive control at inhibiting irrelevant information, and they were slower at recognising Chinese words but quicker at recognising English words. Critically, we also showed that proficient bilinguals showed a smaller Stroop effect than non‐proficient bilinguals in Chinese but a comparable Stroop effect as non‐proficient bilinguals in English. The results cannot be accounted for by cognitive control or word recognition speed alone; instead, they are best accommodated by assuming that cognitive control and word recognition speed jointly determine the Stroop effect. Thus, we conclude that enhanced cognitive control and delayed word recognition combine to reduce Stroop effect in bilinguals as compared to monolinguals.     

Maximum Marginal Likelihood Estimation of a Monotonic Polynomial Generalized Partial Credit Model with Applications to Multiple Group Analysis

We present a semi-parametric approach to estimating item response functions (IRF) useful when the true IRF does not strictly follow commonly used functions. Our approach replaces the linear predictor of the generalized partial credit model with a monotonic polynomial. The model includes the regular generalized partial credit model at the lowest order polynomial. Our approach extends Liang’s (A semi-parametric approach to estimate IRFs, Unpublished doctoral dissertation, 2007) method for dichotomous item responses to the case of polytomous data. Furthermore, item parameter estimation is implemented with maximum marginal likelihood using the Bock–Aitkin EM algorithm, thereby facilitating multiple group analyses useful in operational settings. Our approach is demonstrated on both educational and psychological data. We present simulation results comparing our approach to more standard IRF estimation approaches and other non-parametric and semi-parametric alternatives.     

英语阅读问题解决的认知诊断

本研究尝试将认知诊断技术应用于中学生英语阅读问题解决(ERPS),以实现对中学生英语阅读问题解决的认知诊断,探讨中学生英语阅读问题解决的认知发展特点及其所存在的问题,为中学生的相关认知发展和知识获取服务。研究发现:(1)基于文本表征和反应决策两个加工过程中的七个认知属性是影响中学生ERPS的主要认知成分(R2=0.792);(2)中学生对于文本表征加工过程所涉及的属性的掌握情况优于反应决策加工过程所涉及的属性,学生所面临的主要困主要难于在反应决策加工阶段;(3)对不同属性掌握情况上存在显著的学校类型差异。(4)学生认知掌握状态的类型主要集中在15种(占73%),最多的三种为(1111011)、(1111110)和(1111101)(占34%)。总体来说,学生的属性掌握还是比较好的。相对地,对推理、信息匹配和正确选项的加工水平三个属性掌握较差,应引起重视。     

数学学习困难初中生的记忆广度特点

记忆广度包括短时记忆广度和工作记忆广度,为揭示数学学习困难学生认知缺损特点,筛选103名初中生（平均年龄12.57岁）,比较数学困难学生（49名）与数学优秀学生（54名）的记忆广度差异,通过词语系列任务、阅读广度任务以及倒背数字任务,分别测查了短时记忆、言语工作记忆以及数字工作记忆。结果发现,数困组与优秀组的学生在词语系列任务中没有显著差异（t＝-1.59, p>.05）,在阅读广度任务中,具有显著差异（t＝-2.38, p<.05）,在倒背数字任务中具有极其显著的差异（t＝-4.69, p<.01）。阅读广度和倒背数字之间具有显著相关(r=.24, p<.05),词语系列任务与阅读广度(r=.19, p>.05)和倒背数字任务(r=.05, p>.05)之间不存在显著相关。研究表明,在具有干扰情况的任务更能有效预测数学成绩,数学学习困难的认知缺损主要是对抗干扰的能力不足,而非简单的短时记忆广度。     

HO-DINA模型的MCMC参数估计及模型性能研究

认知诊断目前在国内外越来越受到重视,而要真正实现认知诊断,需借助一定的计量学模型即认知诊断模型。国际上,目前已开发近60种认知诊断模型,不同模型又各具特点。本研究重点分析国外研究较成熟的模型--HO-DINA/DINA模型,具体探讨该模型参数估计的实现及模型性能,采用Monte Carlo模拟方法进行,研究发现：(1)本研究对项目参数、属性参数和被试参数估计返真性较好、稳健性较强、HO-DINA模型具有较高的判断率,MCMC算法可行;（2）诊断的属性个数越多,诊断的模式正确率越低,建议实际使用该模型时,诊断的属性个数不宜超过7个;（3）用于诊断的项目数越多,诊断的模式正确率越高,在实际工作中,若要保证有80%以上的模式判准率,则4个属性的至少需20题,5个、6个和7个属性的至少需要40题,8个属性至少需60题。实际运用者应根据实际情况考虑适当的项目数及属性数。     

Associations of Health-Related Quality of Life with Healthcare Utilization Status in Veterans

Evidence indicates that veterans using VA healthcare services have poor health-related quality of life (HRQOL). Little is known, however, about differences in HRQOL among those who only use VA services and those who also use non-VA services. We sought to evaluate differences in HRQOL among veterans who use: (1) only non-VA services (2) only VA services and (3) both VA and non-VA services (i.e., dual users). A cross-sectional study of 39,942 US veterans who completed the CDC’s 2004 Behavioral Risk Factor Surveillance System (BRFSS) survey was analyzed. Self-rated measures of global health status and the number of days per month that veterans were limited by physical or mental problems were extracted from BRFSS survey data as outcomes. Multivariate logistic regression demonstrated that, compared to those receiving all healthcare outside of VA, veterans receiving VA care were more likely to report poorer health outcomes, including worse global health status, greater impairments in physical functioning, and increased limitations regarding routine activities (p’s ≤ .05). Both exclusive and dual users of VA services reported poorer HRQOL than individuals not using VA services. More research is needed regarding veterans’ health status, particularly in the context of dual use.