Hongyun Liu
Datos Biográficos
| ID | 3655410 |
|---|---|
| NOMBRE | Hongyun Liu |
| NOMBRES | Hongyun |
| APELLIDO | Liu |
| FIRMA | LIU H |
| AFILIACIONES | Beijing Normal University |
| ORCID | 0000-0002-3472-9102 |
| VERIFICADO | Sí |
| TOTAL DE OBRAS | 61 |
| TOTAL DE CITAS | 59 |
| OBRAS COMO AUTOR | 61 |
| OBRAS COMO EDITOR | 0 |
| PRIMER AÑO DE PUBLICACIÓN | 2005 |
| AÑO MÁS RECIENTE DE PUBLICACIÓN | 2026 |
| ÍNDICE H | 5 |
A Two-Step Method Based on lz* for Identifying Effortful Respondents
The likelihood-based person-fit statistic, lz*, is commonly used in educational assessments to distinguish between respondents who are putting in effort and those who are not. However, lz* depends on the estimated item parameters. Item parameter estimates based on data containing non-effortful respondents are biased, thereby undermining the strength of lz*. To address this issue, we propose a two-step method that leverages data mining techniques …
Dynamic Interplay Between State Mindfulness and Distress Tolerance in College Students with Depression
Planned Measurement-Missing Designs in Intensive Longitudinal Studies
High participant burden in intensive longitudinal studies (ILS) often reduces data quality and quantity. Planned measurement missing designs (MMD) can alleviate this burden by lowering data collection frequency or duration while maintaining efficiency. This study proposed and evaluated the complete duration MMD (CD-MMD) and the reduced duration MMD (RD-MMD) within the dynamic structural equation modeling framework using Monte Carlo simulations. C…
The relation between family factors and children’s vocabulary knowledge
Although family factors are considered important for children’s language acquisition, the evidence comes primarily from affluent societies. Thus, this study aimed to examine the relations between family factors (family’s socioeconomic status [SES], home literacy activities, access to print resources, and parental beliefs) and children’s vocabulary knowledge in both urban and rural settings in China. Data from 366 children (urban group: 109, 4.85 …
Data analysis and sample size planning for intensive longitudinal intervention studies using dynamic structural equation modeling
摘要: 密集追踪干预研究具有生态效度高、能够提供实时和个性化干预等优势。然而, 目前常用的数据分析方法未能充分反映密集追踪数据的特点, 而先进的数据分析模型又缺乏与之匹配的样本量规划方法, 极大地限制了这种范式的推广应用。本文在两种典型的密集追踪干预实验设计——单臂设计和随机对照设计下, 基于动态结构方程模型, 结合检验力和效应量估计准确性, 采用模拟研究方法开展样本量规划, 并从第一类错误率等方面对两种设计进行综合比较, 最后提出了实验设计和样本量规划建议
A Mixture Modeling Approach to Detect Different Behavioral Patterns for Process Data
Using student, teacher and family-related factors to predict students’ problem-posing performance
This study explored the predictors of students’ problem-posing performance in mathematics based on 5,068 Chinese seventh-grade students’ responses. Stepwise Regression Model and LASSO were used to detail the relationships among student-, teacher-, and family-related predictors and problem-posing. The findings indicated that, when employing stepwise analysis, students’ cognitive predictors (IQ, computation, cumulative learning, reasoning, reading)…
Dynamic prediction of depressive states using stress processes
摘要: 近年来, 抑郁预测的重要性日渐凸显。以往研究主要在个体间水平考察抑郁的风险因素, 本研究聚焦个体内水平, 结合压力这一关键因素以及日常压力过程模型, 构建压力过程对抑郁状态的动态预测模型。收集356名大学生7天(每天5次)的生态瞬时评估数据, 采用多层决策树的机器学习算法, 发现:(1)含忧虑消极情绪、压力源和反刍的模型能准确预测个体后续(3小时后)有无抑郁状态; (2)不含情绪的预测模型中, 整合当前和预期压力应对、反刍、身体不适感和主观压力感受也能实现对抑郁状态的有效预测; (3)压力过程的多个成分会累积作用于个体, 共同预测后续的抑郁状态; (4)压力过程的累积均值和偏离值动态指标对抑郁状态预测有重要贡献。研究从动态视角开发抑郁状态的实时预警工具, 揭示多种压力过程因素协同预测的复杂组合和影响路径, 深化压力过程对抑郁状态复杂预测模式的理解
Incorporating Qualitative Distinctions in Within-Person Effect Analyses
Within-person effects are getting increasing interest in social and behavioral sciences. Differences in within-person effects are recognized as a key element for understanding between-person differ
Model Selection for Mixed-Effects Location-Scale Models with Confidence Interval for LOO or Waic Difference
LOO (Leave-One-Out cross-validation) and WAIC (Widely Applicable Information Criterion) are widely used for model selection in Bayesian statistics. Most studies select the model with the smallest value based on point estimates, often without considering the differences in fit indices or the uncertainty of the estimates. To address this gap, we propose a sequential method for comparing models based on confidence intervals for ΔLOO or ΔWAIC. A simu…
Modeling Disengaged Survey Responding with Response Times as Predictors
Disengaged responding (DR) poses a major threat to the quality of self-report survey data. Traditional indicator-based detection methods rely on threshold settings and neglect the uncertainty of id
Detrending for Intensive Longitudinal Dyadic Data Analysis Using DSEM
Dynamic Processes of Parent–Adolescent Conflict and Warmth in Chinese Families
Can We Differentiate a Latent Growth Curve Model from Competitors? Evidence Based on Individual Case Residuals
In latent growth curve modeling (LGCM), overall fit indices have garnered increased disputation for model selection, and model fit evaluation based on the mean structure has becoming popularity. The present study developed a versatile fit index, named Weighted Root Mean Squared Errors (WRMSE), based on individual case residuals (ICRs) with the aim of facilitating model selection. Through comparing to various fit indices, this study demonstrated t…
Confidence interval width contours
, , , , , ,
Linear Mixed-Effects Models for Dependent Data
Linear mixed-effects models have been increasingly used to analyze dependent data in psychological research. Despite their many advantages over ANOVA, critical issues in their analyses remain. Due to increasing random effects and model complexity, estimation computation is demanding, and convergence becomes challenging. Applied users need help choosing appropriate methods to estimate random effects. The present Monte Carlo simulation study invest…
Dynamic bidirectional relation between state mindfulness and suicidal ideation among female college students
Research has indicated that mindfulness is a protective factor against suicidal ideation. However, the dynamic reciprocal relation between them has been understudied. In this study, 110 female college students with suicidal ideation completed a measure of trait mindfulness and a 28-day diary of suicidal ideation and three-dimensional state mindfulness, including acting with awareness, present-moment attention, and nonjudgmental acceptance. Dynami…
Relationship between homework time and academic and non‐academic performance in China
Inspired by complex system theory, this study adopts a multilevel piecewise regression model to examine the relationship between homework time and the development of students in different grades using a large‐scale testing database in China. The results indicate that the relationship between homework time and students’ performance is positive when homework time is less than the cut‐off values and becomes negative when homework time is greater tha…
Teacher-student relationship as a protective factor for socioeconomic status, students’ self-efficacy and achievement
Victim profiles and the protective role of school anti-bullying norms
Dynamic and cyclic relationships between employees' intrinsic and extrinsic motivation
Missing data analysis in cognitive diagnostic models
摘要: 认知诊断测评中缺失数据的处理是理论和实际应用者非常关注的研究主题。借鉴随机森林插补法(RFI)不依赖于缺失机制假设的特点, 对已有的RFI方法进行改进, 提出采用个人拟合指标(RCI)确定插补阈值的新方法: 随机森林阈值插补方法(RFTI)。模拟研究表明, RFTI在插补正确率上明显高于RFI方法; 与RFI和EM方法相比, RFTI在被试属性模式判准率和边际判准率上表现出明显优势, 尤其是非随机缺失和混合缺失机制, 以及缺失比例较高的条件下, 其优势更加明显。但对项目参数的估计, RFTI方法与EM方法相比不具有优势
A Monte Carlo Confidence Interval Method for Testing Measurement Invariance
We propose a new method, the Monte Carlo confidence interval (MCCI) method, for studying measurement invariance. This method allows researchers to examine the invariance of all items simultaneously by comparing the observed between-group differences in parameters with those obtained under the null hypothesis of invariance. We compare the performance of our method to two other methods: the multigroup confirmatory factor analysis (MG-CFA) and the f…
Does Socioeconomic Status Matter? Materialism and Self-Esteem
A comparison of standard residual methods and a mixture hierarchical model for detecting non-effortful responses
Assessment datasets contaminated by non-effortful responses may lead to serious consequences if not handled appropriately. Previous research has proposed two different strategies: down-weighting and accommodating. Down-weighting tries to limit the influence of aberrant responses on parameter estimation by reducing their weight. The extreme form of down-weighting is the detection and removal of irregular responses and response times (RTs). The sta…
Phonological skills and vocabulary knowledge mediate socioeconomic status effects in predicting reading outcomes for Chinese children
This study examined the relations among socioeconomic status (SES), early phonological processing, vocabulary, and reading in 262 children from diverse SES backgrounds followed from ages 4 to 9 in Beijing, China. SES contributed to variations in phonological skills and vocabulary in children's early development. Nonetheless, early phonological and vocabulary abilities exerted equally strong and independent mediation of the SES effects on children…
Factors related to parents’ engagement in cognitive and socio-emotional caregiving in developing countries
How socioeconomic status, executive functioning and verbal interactions contribute to early academic achievement in Chinese children
The present study investigated the relative importance of executive functioning, parent-child verbal interactions, phonological awareness and visual skills on reading and mathematics for Chinese children from low-versus middle-socio economic status (SES) backgrounds. A total of 199 kindergarten children were assessed on executive functioning, verbal interactions, phonological awareness, visual skills, mathematics and word reading in Chinese and E…
Examining the relationships between cognitive activation, self-efficacy, socioeconomic status, and achievement in mathematics
BackgroundPrevious studies have suggested that teachers' frequent use of cognitive activation strategies in mathematics lessons is positively associated with students' mathematics achievement.AimsThis study aims to investigate the possible mediating role of mathematics self-efficacy in the association between cognitive activation and achievement in mathematics classrooms. Besides that, we explored the moderating role of students' socioeconomic st…
Growth of Compounding Awareness Predicts Reading Comprehension in Young Chinese Students
Using a longitudinal sample of young Chinese students (fall and spring in grades 1 and 2: times 1–4, respectively) and growth curve analysis, this study examined whether the initial status and growth rates of compounding awareness from time 1 to time 4 uniquely contribute to reading comprehension at time 4 and whether word‐reading efficiency at time 4 mediates the association between initial status and growth in compounding awareness and reading …
Gender differences in mathematics achievement in Beijing
BackgroundThe topic of gender differences in mathematical performance has received considerable attention in the fields of education, sociology, economics and psychology.AimsWe analysed gender differences based on data from the Beijing Assessment of Educational Quality in China.SampleA large data set of Grade 5 and Grade 8 students who took the mathematical test from 2008 to 2013 (n = 73,318) were analysed.MethodMeta-analysis was used in this res…
Changing models across cultures
Understanding chinese developmental dyslexia
Tasks representing 9 cognitive constructs of potential importance to understanding Chinese reading development and impairment were administered to 75 children with dyslexia and 77 age-matched children without reading difficulties in 5th and 6th grade. Logistic regression analyses revealed that dyslexic readers were best distinguished from age-matched controls with tasks of morphological awareness, speeded number naming, and vocabulary skill; perf…
The Use of Multilevel Item Response Theory Modeling in Test Development
摘要: 作者简要介绍了多水平项目反应模型,对多水平项目反应理论与通常项目反应理论之间的关系进行了探讨,得到了多水平项目反应模型参数与通常项目反应模型参数之间的关系,并讨论了多水平项目反应模型的推广模型。通过一个实际例子,用多水平项目反应模型对测验中项目的特征进行分析;检验个体水平和组水平预测变量对能力参数的影响;对项目功能差异进行分析。最后文章就多水平项目反应理论模型的优势与不足进行了讨论
Parameter Estimation of the Raw Item in Computerized Adaptive Testing
摘要: 计算机化自适应测验(Computerized Adaptive Testing, 简称CAT)其安全性面临着新的挑战, 小题库的安全更受威胁。如何建设一个大型、优质的题库成为CAT研究中一个非常重要的课题。目前CAT题库的建设存在一些问题, 如成本高且保密性较差。尤其是等值技术较复杂且锚题重复使用容易造成泄露。如能在实施CAT过程中插入未经过参数估计的项目(原始题), 同时对原始题项目参数进行估计, 这对建设大型、优质的CAT题库来说其意义是不言而喻的。本文基于1PLM和2PLM对此进行研究, 提出了原始题在线估计的新方法以及推导出了求区分度参数a迭代初值的计算公式。研究结果表明:无论是模拟研究还是实证研究, 原始题被作答的次数对项目参数估计结果都会产生不同的影响, 并且原始题作答人数越多项目参数估计精度也越高
The Developing of Faking Detection Scale in Application Situation
摘要: 在应聘情境中, 被试容易对人格测验作假。应对作假的常用方法是采用社会称许性量表对作假直接测量, 再去校正和识别作假效应。但是采用社会称许性量表测量作假存在很多问题, 因而基于作假的特殊性质开发了《作假识别量表》。采用探索性因素分析证实了量表的单维性, 解释率为54.650%。概化理论检验表明测验信度较好, G系数为0.906, j系数为0.902。采用一个真实的应聘情境检验效度, 发现《作假识别量表》对作假更加敏感, 能够比较充分地测量作假
What is in the naming? A 5-year longitudinal study of early rapid naming and phonological sensitivity in relation to subsequent reading skills in both native Chinese and English as a second language.
Among 262 Chinese children, syllable awareness and rapid automatized naming (RAN) at age 5 years and invented spelling of Pinyin at age 6 years independently predicted subsequent Chinese character recognition and English word reading at ages 8 years and 10 years, even with initial Chinese character reading ability statistically controlled. In addition, reading fluency in Chinese was predicted by RAN but not by phonological sensitivity, whereas Ch…
Chinese children's character recognition
Tasks tapping visual skills, orthographic knowledge, phonological awareness, speeded naming, morphological awareness and Chinese character recognition were administered to 184 kindergarteners and 273 primary school students from Beijing. Regression analyses indicated that only syllable deletion, morphological construction and speeded number naming were unique correlates of Chinese character recognition in kindergarteners. Among primary school chi…
When Should We Use Testlet Model? A Comparison Study of Bayesian Testlet Random-Effects Model and Standard 2-PL Bayesian Model
摘要: 题组模型可以解决传统IRT模型由于题目间局部独立性假设违背时所导致的参数估计偏差。为探讨题组随机效应模型的适用范围, 采用Monte Carlo模拟研究, 分别使用2-PL贝叶斯题组随机效应模型(BTRM)和2-PL贝叶斯模型(BM)对数据进行拟合, 考虑了题组效应、题组长度、题目数量和局部独立题目比例的影响。结果显示:(1) BTRM不受题组效应和题组长度影响, BM对参数估计的误差随题组效应和题组长度增加而增加。(2) BTRM具有一定的普遍性, 且当题组效应大, 题组长, 题目数量大时使用该模型能减少估计误差, 但是当题目数量较小时, 两个模型得到的能力估计误差都较大。(3)当局部独立题目的比例较大时, 两种模型得到的参数估计差异不大
Item Parameter Estimation for Multidimensional Measurement
摘要: 作者简要回顾了SEM框架下分类数据因素分析(CCFA)模型和MIRT框架下测验题目和潜在能力的关系模型, 对两种框架下的主要参数估计方法进行了总结。通过模拟研究, 比较了SEM框架下WLSc和WLSMV估计方法与MIRT框架下MLR和MCMC估计方法的差异。研究结果表明:(1) WLSc得到参数估计的偏差最大, 且存在参数收敛的问题; (2)随着样本量增大, 各种项目参数估计的精度均提高, WLSMV方法与MLR方法得到的参数估计精度差异很小, 大多数情况下不比MCMC方法差; (3)除WLSc方法外, 随着每个维度测验题目的增多参数估计的精度逐渐增高; (4)测验维度对区分度参数和难度参数的影响较大, 而测验维度对项目因素载荷和阈值的影响相对较小; (5)项目参数的估计精度受项目测量维度数的影响, 只测量一个维度的项目参数估计精度较高。另外文章还对两种方法在实际应用中应该注意的问题提供了一些建议
Applying IRT_ΔB Procedure and Adapted LR Procedure to Detect DIF in Tests with Matrix Sampling
摘要: 矩阵取样测验包含多个题册, 单个题册的总分不能直接作为匹配变量用于DIF检测。本研究首先基于模拟数据, 同时采用IRT_Δb法, 以及用IRT模型估计的考生能力作为匹配变量修订后的LR法对矩阵取样测验进行DIF检测, 分析二者进行DIF检测的有效性及其相关影响因素; 并根据已有的LR法DIF判断标准划定出IRT_Δb法分类标准; 最后使用实证数据加以验证。结果显示:矩阵取样测验中, IRT_Δb法和修正LR法均能较好地区分DIF量不同的题目; 样本量、题册中DIF题目的比例和考生群体间真实能力的差异对两种方法的检验力、犯I类错误的概率和分类结果都有较大影响
Testing Measurement Equivalence of Categorical Items’ Threshold/Difficulty Parameters
Mediation Analysis for Ordinal Outcome Variables
摘要
Comparison of Mirt Linking Methods for Different Common Item Designs
摘要: 实际应用中测验往往具有多维结构, 如果仍采用单维IRT方法进行等值, 会得到不准确的结果。因此对于多维结构的测验, 需要使用多维IRT等值方法来实现参数的转换。基于共同题设计, 文章通过模拟研究的方法, 考察了不同铆测验设计下几种多维IRT等值方法的表现, 同时考虑了测验长度、两个维度题目数量的比例、铆测验长度、铆测验的选择策略、两个维度之间的相关和等值群体的能力水平差异六个因素的影响。所比较的多维IRT等值方法有:均值/均值(MM)方法, 均值/标准差(MS)方法, Stoking-Lord (SL)方法, Haebara (HB)方法, 最小平方(LS)方法。结果显示:(1) SL, HB和LS方法得到的等值误差均方根最小, 且在各条件下表现较为稳定。(2) MM和MS方法在非等组条件下呈现出很大的误差均方根。(3)铆测验设计对SL, HB和LS方法的等值结果没有显著影响。(4)在两个维度之间的相关较高, 测验长度和铆测验长度较长, 等值群体的能力水平没有差异的条件下, SL…
Phonological skills and vocabulary knowledge mediate socioeconomic status effects in predicting reading outcomes for Chinese children
This study examined the relations among socioeconomic status (SES), early phonological processing, vocabulary, and reading in 262 children from diverse SES backgrounds followed from ages 4 to 9 in Beijing, China. SES contributed to variations in phonological skills and vocabulary in children's early development. Nonetheless, early phonological and vocabulary abilities exerted equally strong and independent mediation of the SES effects on children…
Factors of Piecewise Growth Mixture Model
摘要
Development of Preschoolers' Emotion and False Belief Understanding
To explore the developmental trajectory of emotions (happiness, sadness, anger, and fear) and false belief understanding (an unexpected-location and an unexpected-contents task), we measured the performance of 3- and 4-year-olds 4 times at approximately half-yearly intervals. The results indicated that the children's ability to understand emotions and false beliefs increased significantly at each time point in the first year and a half, but no si…
Factors related to parents’ engagement in cognitive and socio-emotional caregiving in developing countries
The role of collective perception of school psychological environment in grades 4~6 students' academic achievement
摘要
How socioeconomic status, executive functioning and verbal interactions contribute to early academic achievement in Chinese children
The present study investigated the relative importance of executive functioning, parent-child verbal interactions, phonological awareness and visual skills on reading and mathematics for Chinese children from low-versus middle-socio economic status (SES) backgrounds. A total of 199 kindergarten children were assessed on executive functioning, verbal interactions, phonological awareness, visual skills, mathematics and word reading in Chinese and E…
Multidimentional Rasch Testlet Model
摘要: 本文将多维随机系数多项Logistic模型(MRCMLM)拓展应用到多维题组领域, 得到适用于多维目标能力和多维题组效应的多维题组反应模型(MTRM), 该模型具有高度灵活性和适用性。本文通过两个模拟研究和一个应用研究探究MTRM参数估计精度和模型适用性, 以及与two-tier模型的差异, 结果发现:(1)能力维度间相关和项目评分等级是影响模型参数估计的重要因素; (2) MTRM对项目参数估计准确性和稳定性高于two-tier模型, 对题组效应大小估计更为准确。(3) MTRM在考虑项目内多维题组情况下模型拟合度更高, 为测验分析提供了更广泛的模型结构选择, 具有显著的应用价值
Reporting overall scores and domain scores of bi-factor models
摘要: 双因子模型可以同时包含一个全局因子和多个局部因子, 在描述多维测验结构时有其独特优势, 近些年应用越来越广泛。文章基于双因子模型, 提出了4种合成总分和维度分的方法, 分别是:原始分法, 加和法, 全局题目加权加和法和局部题目加权加和法, 并采用模拟的方法, 在样本量、测验长度、维度间相关变化的条件下考察了这些方法与传统多维IRT方法的表现。最后, 通过实证研究对结果进行了验证。结果显示:(1)全局加权加和法和局部加权加和法, 尤其是局部加权加和法合成的总分和维度分与真值最接近、信度最高。(2)在维度间相关较高, 测验长度较长的条件下, 局部加权加和法的结果较好, 部分条件下甚至优于多维IRT法。(3)仅有局部加权加和法合成的维度分能够反应维度间真实的相关关系
LGM-based analyses with missing data
摘要
Growth of Compounding Awareness Predicts Reading Comprehension in Young Chinese Students
Using a longitudinal sample of young Chinese students (fall and spring in grades 1 and 2: times 1–4, respectively) and growth curve analysis, this study examined whether the initial status and growth rates of compounding awareness from time 1 to time 4 uniquely contribute to reading comprehension at time 4 and whether word‐reading efficiency at time 4 mediates the association between initial status and growth in compounding awareness and reading …
Gender differences in mathematics achievement in Beijing
BackgroundThe topic of gender differences in mathematical performance has received considerable attention in the fields of education, sociology, economics and psychology.AimsWe analysed gender differences based on data from the Beijing Assessment of Educational Quality in China.SampleA large data set of Grade 5 and Grade 8 students who took the mathematical test from 2008 to 2013 (n = 73,318) were analysed.MethodMeta-analysis was used in this res…
让自适应测验更知人善选——基于推荐系统的选题策略
Better CAT item selection strategies may be designed by making better use of information from previous examinees’ responses. The past examinees’ data serve as a valuable reference for selecting items more accurately and evenly for new examinees. However, most of the existing strategies proposed under the theoretical framework of IRT only use information from the current examinee and fail to take full advantage of past examinees’ data. A collabora…
Psychology (38 obras) · Mathematics (32 obras) · Statistics (29 obras) · Computer Science (22 obras) · Econometrics (21 obras) · Developmental psychology (17 obras) · Social Psychology (12 obras) · Data mining (10 obras) · Psychometric Methodologies and Testing (10 obras) · Artificial Intelligence (9 obras)