一种高效的CD-CAT在线标定新方法：基于熵的信息增益与EM视角

项目增补(Item Replenishing)对认知诊断计算机自适应测验(CD-CAT)题库的维护有着至关重要的作用, 而在线标定是一种重要的项目增补方式。基于数据挖掘中特征选择(Feature Selection)的思路, 提出一种高效的基于熵的信息增益的在线标定方法(记为IGEOCM), 该方法利用被试在新旧题上的作答联合估计新题的Q矩阵和项目参数。研究采用Monte Carlo模拟实验验证所开发新方法的效果, 并同时与已有的在线标定方法SIE、SIE-R-BIC和RMSEA-N进行比较。结果表明：新开发的IGEOCM在各实验条件下均具有较好的项目标定精度和项目估计效率, 且整体上优于已有的SIE等方法; 同时, IGEOCM标定新题所需的时间低于SIE等方法。总之, 研究为CD-CAT题库中项目的增补提供了一种更为高效、准确的方法。     

认知诊断模型资料拟合检验方法和统计量

认知诊断模型界定了测验题目和所考察属性之间的关系, 通过被试的作答反应获取被试对属性或知识技能的掌握情况。认知诊断模型资料拟合检验可以从项目拟合、模型绝对拟合、模型相对拟合和个人拟合方等方面进行。通过对认知诊断拟合检验方法和统计量的详细介绍和评价, 可为认知诊断实践提供借鉴和参考。未来研究可在更丰富的研究条件下对各统计量的性能进行评价和对比, 完善已有的拟合检验方法, 提出新的拟合统计量。     

The Adolescent Behavior Checklist: Validation Using Structured Diagnostic Interviews

The purpose of this study was to evaluate the discriminant validity of scores from the Adolescent Behavior Checklist (ABC), a self-report measure of ADHD symptomatology for adolescents ages 11–17 years. Validity was assessed through correlational, univariate, and discriminant function analyses using three groups: (1) adolescents diagnosed with ADHD, (2) adolescents currently experiencing a mood and/or anxiety disorder, and (3) adolescents with no major psychological disorder. Convergent and divergent validity of the ABC factor scores was demonstrated through correlational results with (1) parent and adolescent report of ADHD symptoms during structured psychiatric interviews and (2) scores on questionnaires measuring related and nonrelated constructs. Univariate analyses indicated that the ADHD group obtained significantly higher scores than did the nonclinical adolescents across all ABC factors. Additionally, the ADHD group scored significantly higher than did the psychiatric controls on the following ABC factors: Conduct Problems, Impulsivity/Hyperactivity, and Social Problems. Results from discriminant analyses supported the reliability of ABC scores in correctly classifying participants into groups. Compared to the Youth Self-Report, the ABC was found to be somewhat better at classifying when used in a multiinformant discriminant analysis. Therefore, overall results from the current study suggest that the ABC is a valid and useful self-report screening measure for ADHD symptoms and related difficulties.     

认知诊断计算机自适应测验中平衡属性收敛的新方法

提出两种认知诊断计算机自适应测验下平衡属性收敛的新方法（MABI、RTA）,模拟研究系统探讨和比较了此二者与已有方法（ABI、IABI和RABI）的表现。结果发现：（1）新方法较不考虑属性收敛的方法有更高的准确率以及更均衡的题目使用率;（2）新方法较ABI和RABI有稍低的准确性,但有更平衡的题目使用率;（3）新方法与IABI的准确性和题目使用率在不同选题策略下各有合优势。总之,两种新方法较好地兼顾测量准确性、题目使用率以及题库曝光情况。     

Virtually overcoming grammar learning with 3D application of Loci mnemonics?

The importance of contextual information for memory organization has been advocated by memory research and ancient mnemonic techniques (e.g., method of loci), yet it remains overlooked in most current study environments. Here, German noun gender was presented to 48 participants without prior knowledge of German, either without or within a provided spatial context consisting of a simulated virtual environment that could be explored freely. The three main findings were: in addition to reduced forgetting rate, memory was significantly enhanced when acquisition had occurred with a spatial context than without, in immediate, and delayed cued recall, as well as in delayed free recall. Second, visualization ability predicted spatial context efficiency as a memory aid for cued recall. Lastly, performance of the method of loci‐based method correlated with its perceived efficiency. This is the first study to experimentally demonstrate the potential effectiveness of computer‐induced spatial context on grammar learning.     

Goal-setting in diabetes self-management: A systematic review and meta-analysis examining content and effectiveness of goal-setting interventions

Background: Goal-setting is recommended and widely used within diabetes self-management programmes. However, empirical evidence around its effectiveness lacks clarity. This review aims to evaluate the effectiveness of goal-setting interventions on diabetes outcomes and to determine which behaviour change techniques (BCTs) are frequently used within these interventions.

Methods: A systematic search identified 14 studies, describing 12 interventions targeting diabetic-control which incorporated goal-setting as the main intervention strategy. Study characteristics, outcome measures and effect sizes of the included studies were extracted and checked by two authors. The BCT taxonomy v1 was used to identify intervention content. Meta-analyses were conducted to assess intervention effects on the primary outcome of average blood glucose levels (HbA1c) and on body-weight. Psycho-social and behavioural outcomes were summarised in narrative syntheses.

Results: Significant post-intervention improvements in HbA1C were found (?.22, 95% CI, ?.40, ?.04) across studies. No other main effects were identified. The BCT ‘goal-setting (behaviour)’ was most frequently implemented and was identified in 84% of the interventions.

Conclusions: Goal-setting interventions appear to be associated with reduced HbA1C levels. However, the low numbers of studies identified and the risk biases across studies suggest more research is needed to further explore goal-setting BCTs in diabetes self-management.     

On Interim Cognitive Diagnostic Computerized Adaptive Testing in Learning Context

Interim assessment occurs throughout instruction to provide feedback about what students know and have achieved. Different from the current available cognitive diagnostic computerized adaptive testing (CD-CAT) design that focuses on assessment at a single time point, the authors discuss several designs of interim CD-CAT that are suitable in the learning context. The interim CD-CAT differs from the current available CD-CAT designs primarily because students’ mastery profile (i.e., skills mastery) changes due to learning, and new attributes are added periodically. Moreover, hierarchies exist among attributes taught sequentially and such information could be used during item selection. Two specific designs are considered: The first one is when new attributes are taught in Stage II, but the student mastery status of the previously taught attributes stays the same. The second design is when both new attributes are taught, and previously taught attributes can be further learned or forgotten in Stage II. For both designs, the authors propose an individual prior, which considers a person’s learning history and population learning model, to start an interim CD-CAT. Simulation results show that the Stage II CD-CAT using individual prior outperforms the methods using population priors. The GDINA (generalized deterministic inputs, noisy, “and” gate) diagnostic index (GDI) is extended to accommodate item hierarchies, and analytic results are provided to further illustrate the types of items that are most popular during item selection. As the first study that focuses on the application of CD-CAT in a learning context, the methods and results present herein showed the great promise of using CD-CAT to monitor learning.     

基于选项层面的认知诊断非参数方法

充分挖掘选择题(Multiple-Choice, MC)的诊断信息受到了较多关注, 将干扰项信息考虑在内可以提升诊断精度。为了弥补参数模型基于大样本才能获得可靠估计的不足, 以及适用于班级水平的小样本诊断测验情境, 本研究提出了非参数的多选题诊断方法。模拟和实证研结果表明：(1)当MC测验中题目参数不存在较大差异时, ${{d}_{\text{ph}-\text{MC}}}$法在多数情况下表现优于参数类诊断模型。(2)当MC测验中题目参数存在较大差异时, ${{d}_{ph-MC}}$法的表现最优。(3)实证研究中非参数方法和参数类模型的分类一致性程度较高, ${{d}_{\text{ph}-\text{MC}}}$距离法估计得到的考生属性总体掌握程度与总分相关最高。最后, 基于MC诊断测验的特点提出了若干研究方向。     

What is the best way to promote cycling? A systematic review and meta-analysis

Cycling has the potential to address a number of personal and societal challenges, not least with respect to health and the need for more sustainable modes of transport. However, the best way(s) to promote cycling is still unclear. In an effort to answer this question, we identified 39 interventions designed to promote cycling, with a total sample of 46,102 participants. Random effects meta-analysis estimated a small but statistically significant effect of interventions on cycling behaviour (g₊ = 0.14, 95% CI [0.05, 0.23]). To identify the most effective intervention strategies, we coded the behaviour change techniques used within each of the interventions. Interventions that prompted people to self-monitor their behaviour or added objects to the environment (e.g., provided shared bikes) were more effective than those that did not use these strategies. Interventions that restructured the physical environment (e.g., built new cycle paths) were less effective than the studies that did not do this. We also identified a number of factors that moderated the effect of the interventions on outcomes; specifically, interventions that targeted a specific group, used objective measures of cycling such as accelerometers, and that were tested using independent groups designs typically yielded stronger effects. The findings should help to guide interventions to promote cycling in the future.     

First Among Equals: Hybridization of Cognitive Diagnostic Assessment and Evidence-Centered Game Design

The objective of the present article is to explore differences and similarities between cognitive diagnostic assessment (CDA) and evidence-centered game design (ECgD) in the service of intentional hybridization. Although some testing specialists might argue that both are essentially the same given their origins in principled assessment design and equivalency of measurement models, this view misses differences in their focus and operationalization. Given the strengths of both CDA and ECgD, there is motivation to consider ways in which each can deliberately inform the other. The intentional hybridization of CDA and ECgD has, at least in principle, significant advantages to produce a stronger offspring than either parent alone. The article includes four sections: (1) conceptual differences between CDA and ECgD, (2) conceptual similarities between CDA and ECgD, (3) challenges with CDA and ECgD, including narrowness of cognitive models, fidelity with learning, ocean of data, sensitivity to diverse learners, reliance on multidimensional psychometric models, and how hybridization may help, and (4) implications for educational assessment in the twenty-first century around the globe.