成对数据的主客体互依模型在MPLUS中的实现

目的在介绍主客体互依模型(Actor-partner interdependence model,APIM)基本思想的基础上,提供构建APIM的MPLUS语句,为AIPM理论在实际研究中的运用奠定基础。方法介绍APIM模型的基本思想及数据格式,运用MPLUS软件进行可区分的成对数据(Distinguishable data)和不可区分的成对数据(Indistinguishable data)的APIM构建。结果对于可区分的成对数据,MPLUS软件能提供简单实用的结构方程模型构建语句,而对于不可区分的成对数据,MPLUS软件在构建结构方程模型的过程中需要限定对子中两成员的6对参数相等。结论结构方程模型是实现可区分的成对数据APIM的最简单方法,也是不可区分的成对数据APIM的准确估计方式,MPLUS则提供了构建结构方程的简洁语句。     

混合响应类型的多水平模型在重复测量资料中的应用和实现

目的将混合响应类型的多水平模型应用到具有两个不同类型结局变量的重复测量资料的分析中。方法对原始资料的格式作适当变换,构造一个水平1虚拟变量,将2个结局变量作为水平1上的观察单位,各时间点的重复测量为水平2单位,受试者为水平3单位,用MLwiN2.25软件拟合混合响应类型的三水平模型,对试验组和对照组的疗效,以及受试者的年龄、性别、观察指标的基线值,时间、组别和时间的交互效应进行分析。结果该模型在考虑了两个不同类型的结局变量在各个水平上的相关性后,可以对两个结局变量同时进行影响因素分析,获得解释变量对两个结局变量影响的估计,且只要数据缺失随机则估计是有效且无偏的。结论由于混合响应类型的多水平模型允许结局变量具有不同类型,并且把数据间的相关性分解为重复测量相关性和结局变量间相关性两部分,可有效地进行重复测量资料的动态变化趋势分析,分析结果更为细致。     

边际回归模型方法及医学应用

目的探讨边际回归模型在医学研究领域多变量相关分析中的应用。方法结合两个医学研究实例，说明边际回归模型原理，软件和实际应用。结果连续型和二分类的多变量需要使用不同的相关测量。对两种类型资料。边际回归模型都可以同时估计回归系数和关联参数。结论边际回归模型方法应用灵活、方便，可作为多变量相关分析的常规工具之一。     

纵向数据潜变量增长曲线模型及其在Mplus中的实现

探讨纵向数据潜变量增长曲线模型及其在Mplus中的实现方法。通过实例采用Mplus软件处理某高校大学生心理健康状况纵向数据。结果表明潜变量增长曲线模型可以处理含有潜变量的纵向数据，能够比较总体发展趋势和个体发展的差异，纳入协变量可以提高模型拟合效果；采用Mplus软件实现潜变量增长曲线模型，程序简单，操作方便。纵向数据潜变量增长曲线模型及其在Mplus中的实现程序，可为实际应用尤其是流行病学队列研究提供统计方法学方面的指导和参考。     

线性混合效应模型的惩罚变量选择

目的研究基于惩罚的线性混合效应模型变量选择原理和方法。方法对线性混合效应模型中的固定效应施加惩罚,采用Lasso和SCAD进行变量选择,通过两步迭代算法估计惩罚似然,利用BIC原则选择惩罚参数。通过广泛的模拟研究评价Lasso和SCAD在线性混合效应模型变量选择中的性质表现,并应用于真实数据的数量性状位点选择。结果模拟研究和实际应用显示,在线性混合效应模型中,两步迭代算法简单可行,基于惩罚的变量选择方法能够有效识别有意义的协变量。结论基于惩罚的策略为线性混合效应模型提供了行之有效的变量选择方法。     

多水平模型和潜变量增长曲线模型在纵向数据分析中的应用及比较

比较多水平模型和潜变量增长曲线模型在纵向数据分析中的应用。文中以结直肠癌患者术后的生命质量情况为实例，比较两种方法的异同。结果表明两方法的参数估计值结果非常接近，多水平模型在模型构建时较为容易，而潜变量增长曲线模型在模型评价等方面具有优势。两方法均可很好地分析纵向观测的数据，且各有优点，研究者应根据需要选择合适的方法分析数据。     

基于潜变量得分的多水平多变量回归模型在职业紧张评价中的应用

目的介绍基于潜变量得分的多水平多反应变量回归模型在职业紧张评价中的应用。方法为克服测量误差的存在，以职业紧张量表14个分项的潜变量得分，将之作为中问结果引入多水平多反应变量回归模型。结果职业任务各分项不同程度地引起职业紧张，而个体应变能力是减轻职业紧张行之有效的方式。随机系数反映这些影响在不同科室存在着不同。结论采用基于潜变量得分的多水平多反应变量回归模型既可有效降低测量误差，又得以合理地解释。尤其对于系统结构数据，多元线性模型的多水平理论比多水平潜变量分析方法更成熟可信。     

环境健康综合数据质量核查与评估初步研究

目的建立环境健康综合数据质量核查评估方法模型,并以某市环境健康数据对该方法模型进行验证,探索适用于环境健康综合监测等大规模数据质量的核查方法。方法基于文献调研,构建环境健康综合数据质量核查评估方法模型;将模型应用于某市2013—2015年环境健康综合数据质量评估中,首先评价环境数据(空气质量数据、气象数据)和健康数据(死因数据、慢病监测数据)的各项核查指标,然后通过综合指数法计算各类数据质量的综合指数。结果该方法模型能够对环境健康综合数据进行有效的评估,可识别各类数据具体问题且实现不同类型、不同年份间数据质量的对比。单项指标核查结果表明某市2013—2014年环境因素数据的缺失率最高,为5.75%,2014—2015年健康效应数据的逻辑错误率高于10%;综合指数评价结果表明健康效应数据质量相比环境因素数据存在问题较多。结论本研究所建立的方法模型可操作性较强,能够为环境健康综合监测等全国大规模监测数据质量核查提供有效工具。     

混合线性模型的应用

目的介绍混合线性模型的结构，固定效应项和随机效应的含义。对具有内部相关性的资料．宣选用混合线性模型进行配合。方法用一个具有聚集性结构的例子和一个重复测量的例子说明配合混合线性模型的方法和步骤。结果分析了资料的层次结构，识别不同层次上的协变量，讨论了模型中固定效应矩阵和随机效应矩阵的结构，使模型参数估计值更易于理解和解释。由于混合线性模型克服了一般线性模型对反应变量必须具有独立和等方差的要求，从而扩大了线性模型的应用范围。对于具有聚集性质的资料及重复测量资料具有很好的拟合效果。结论这一模型计算较复杂，应用SAS／STAT软件包中的PROMIXED过程能很好地解决计算问题。     

结构方程模型在健康素养分析中的应用

目的 探索结构方程模型在健康素养分析中的应用,为建立符合理论和实际的健康素养评价体系提供依据.方法 采用武汉市居民健康素养调查数据,构建结构方程模型,评估在健康素养分析中应用价值.结果 结构方程模型拟合良好,测量模型诠释了潜在变量与测量变量之间的关系,结构模型反映了潜在变量间的关系,模型选择的测量变量是健康素养的核心组...     

Subgroups Analysis when Treatment and Moderators are Time-varying

Prevention scientists are often interested in understanding characteristics of participants that are predictive of treatment effects because these characteristics can be used to inform the types of individuals who benefit more or less from treatment or prevention programs. Often, effect moderation questions are examined using subgroups analysis or, equivalently, using covariate × treatment interactions in the context of regression analysis. This article focuses on conceptualizing and examining causal effect moderation in longitudinal settings in which both treatment and the putative moderators are time-varying. Studying effect moderation in the time-varying setting helps identify which individuals will benefit more or less from additional treatment services on the basis of both individual characteristics and their evolving outcomes, symptoms, severity, and need. Examining effect moderation in these longitudinal settings, however, is difficult because moderators of future treatment may themselves be affected by prior treatment (for example, future moderators may be mediators of prior treatment). This article introduces moderated intermediate causal effects in the time-varying setting, describes how they are part of Robins’ Structural Nested Mean Model, discusses two problems with using a traditional regression approach to estimate these effects, and describes a new approach (a two-stage regression estimator) to estimate these effects. The methodology is illustrated using longitudinal data to examine the time-varying effects of receiving community-based substance abuse treatment as a function of time-varying severity (or need).     

Kernel machine methods for integrative analysis of genome‐wide methylation and genotyping studies

Many large GWAS consortia are expanding to simultaneously examine the joint role of DNA methylation in addition to genotype in the same subjects. However, integrating information from both data types is challenging. In this paper, we propose a composite kernel machine regression model to test the joint epigenetic and genetic effect. Our approach works at the gene level, which allows for a common unit of analysis across different data types. The model compares the pairwise similarities in the phenotype to the pairwise similarities in the genotype and methylation values; and high correspondence is suggestive of association. A composite kernel is constructed to measure the similarities in the genotype and methylation values between pairs of samples. We demonstrate through simulations and real data applications that the proposed approach can correctly control type I error, and is more robust and powerful than using only the genotype or methylation data in detecting trait‐associated genes. We applied our method to investigate the genetic and epigenetic regulation of gene expression in response to stressful life events using data that are collected from the Grady Trauma Project. Within the kernel machine testing framework, our methods allow for heterogeneity in effect sizes, nonlinear, and interactive effects, as well as rapid P‐value computation.     

The doctor as focus group moderator--shifting roles and negotiating positions in health research

BACKGROUND: Any research is inextricably entwined with the researcher's positions adopted while collecting data. This represents an important challenge to focus group moderators whose positions within the group influence data collection. This situation is particularly important in health research where moderators are doctors. OBJECTIVES: This study explores the moderator's social interaction with the group, in particular the moderator's position and how it affects data collection, the research process and knowledge production. METHODS: A qualitative study exploring group dynamics and the moderator's positions in focus group discussions, in particular the interaction between the moderator's position and her role as a doctor. RESULTS: The social construction and negotiation of the doctor's position depended both on the participants' view of the moderator and on the moderator's situational response. The moderator dealt with the participants' expectations and alternated between different positions: those she chose for herself and those chosen for her by the participants. Adoption of an active strategy outlining the moderator's position clarified the framework of data collection. CONCLUSIONS: Doctors using focus groups as research tool to gain insight into people's ideas about illness must be conscious about how their medical background influences their positions during data collection. The focus group moderator must balance between letting participants discuss the topics without being disturbed and actively intervening in the discussion to clarify the process. The researcher has to set the boundaries and guidelines as to how the research is conducted.     

Predicting levels of stress from biological assessment data: empirical models from the Eastern Corn Belt Plains,Ohio, USA

Interest is increasing in using biological community data to provide information on the specific types of anthropogenic influences impacting streams. We built empirical models that predict the level of six different types of stress with fish and benthic macroinvertebrate data as explanatory variables. Significant models were found for six stressor factors: stream corridor structure; siltation; total suspended solids (TSS), biochemical oxygen demand (BOD), and iron (Fe); chemical oxygen demand (COD) and BOD; zinc (Zn) and lead (Pb); and nitrate and nitrite (NOx) and phosphorus (P). Model R2 values were lowest for the siltation factor and highest for TSS, BOD, and Fe. Model R2 values increased when spatial relationships were incorporated into the model. The models generally performed well when applied to a random subset of the data. Performance was more mixed when models were applied to data collected from a previous time period, perhaps because of a change in the spatial structure of these systems. These models may provide a useful indication of the levels of different stresses impacting stream reaches in the Eastern Corn Belt Plains ecoregion of Ohio, USA. More generally, the models provide additional evidence that biological communities can serve as useful indicators of the types of anthropogenic stress impacting aquatic systems.     

从创新扩散视角看优质医疗资源扩容影响因素——基于中国胸痛中心建设的实证研究

目的：本研究在创新扩散理论视角下,分析中国胸痛中心扩散影响因素,为优质医疗资源扩容提供参考依据。方法：收集我国大陆地区31个省级行政区2014—2022年胸痛中心面板数据,以随机效应模型和固定效应模型为基本模型,创新运用空间杜宾模型,定量分析我国胸痛中心建设创新扩散影响因素。结果：固定效应模型与空间杜宾模型结果保持一致。公众需求没有对胸痛中心采用率产生显著影响,政策支持、经济水平、城镇化水平均对胸痛中心采用率产生正向影响。空间杜宾模型进一步证实了公共服务创新扩散存在邻近效应。结论：建议市县各级卫生健康行政部门对辖区胸痛中心建设予以政策支持。采取输送技术、结对帮扶等方式,提高经济发展水平较低地区胸痛中心建设成功率。通过学术会议、交流培训等方式改善农村地区学术信息滞后、信息茧房现状。     

National Human Exposure Assessment Survey: analysis of exposure pathways and routes for arsenic and lead in EPA Region 5

The National Human Exposure Assessment Survey (NHEXAS) Phase I field study conducted in EPA Region 5 (Great Lakes Area) provides extensive exposure data on a representative sample of approximately 250 residents of the region. Associated environmental media and biomarker (blood, urine) concentration data were also obtained for the study participants to aid in understanding of the relationships of exposures to both contaminant pathways and doses. Besides fulfilling the primary NHEXAS objectives, the NHEXAS data provided an opportunity to explore secondary usages, such as examining pathway to route of exposure relationships. A generic type of structural equation model was used to define the anticipated relationships among the various data types for both arsenic (As) and lead (Pb). Since, by design, only a few participants provided data for all sample types, implementing this model required that some media concentrations (outdoor air and soil) be imputed for subjects with missing information by using measurements collected in the same geographic area and time period. The model, and associated pairwise correlations, generally revealed significant but weak associations among the concentrations, exposures, and doses; the strongest associations occurred for the various air measurements (indoor versus outdoor and personal). The generally weak associations were thought to be partly due to the absence of complete coverage of nonresidential environmental media and to nonsynchronization of relevant measurement times and integration periods of collection across the various sample types. In general, relationships between the NHEXAS questionnaire data and the various concentration, exposure, and body-burden measures were also weak. The model results and the modeling exercise suggest several ways for optimizing the design of future exposure assessment studies that are aimed at supporting structural modeling activities.     

A meta-analysis of the effectiveness of health belief model variables in predicting behavior

The Health Belief Model (HBM; Rosenstock, 1966) was constructed to explain which beliefs should be targeted in communication campaigns to cause positive health behaviors. The model specifies that if individuals perceive a negative health outcome to be severe, perceive themselves to be susceptible to it, perceive the benefits to behaviors that reduce the likelihood of that outcome to be high, and perceive the barriers to adopting those behaviors to be low, then the behavior is likely for those individuals. A meta-analysis of 18 studies (2,702 subjects) was conducted to determine whether measures of these beliefs could longitudinally predict behavior. Benefits and barriers were consistently the strongest predictors. The length of time between measurement of the HBM beliefs and behavior, prevention versus treatment behaviors, and drug-taking regimens versus other behaviors were identified as moderators of the HBM variables' predictive power. Based on the weakness of two of the predictors, the continued use of the direct effects version of the HBM is not recommended.     

基于偏最小二乘通径模型的全科医学病人满意度分析

目的 采用偏最小二乘通径模型,分析社区卫生服务机构病人满意度及其各个维度之间的关系.方法 使用本土化后的皇家澳大利亚全科医生学会(RAC GP)“全科医学病人满意度监测工具”,在北京市的两家社区卫生服务中心进行满意度调查.对调查所得数据采用偏最小二乘通径模型建模.结果 根据有关理论设计结构模型1,显示硬件设施感知对技术水平感知、技术水平感知对总体满意度的通径系数较小,且没有通过检验.删去两项关系后,重新建立结构模型2.模型2外部载荷系数都达到0.8以上,总体满意度、技术水平感知和病人知情感知的测量系数分别为0.41、0.89、0.80,模型中各项关系也都得到合理解释.其中人际方面感知和病人知情感知是影响总体满意度的主要因素.结论 偏最小二乘通径模型是分析全科医学中病人满意度及其各维度间关系的有效方法,改善医患交流和加强病人知情教育是提高病人满意度的重点.     

Polychotomous logistic regression methods for matched case-control studies with multiple case or control groups

Two statistical methods, a polychotomous and pairwise approach, are presented to derive estimates of the relative odds in a matched case-control design when multiple case or control groups are used. Test statistics are derived to determine if the relative odds between groups are different. The polychotomous method is limited to case-control sets, i.e., where data are available on all members of a matched set. In contrast, the pairwise method makes use of data from both complete and incomplete sets. Nonetheless, efficiency calculations show that the polychotomous logistic regression model is more efficient even when 40 per cent of the case-control sets are incomplete. An example using a single dichotomous variable is provided.     

Analyzing multivariate survival data using composite likelihood and flexible parametric modeling of the hazard functions

In this paper, we model multivariate time‐to‐event data by composite likelihood of pairwise frailty likelihoods and marginal hazards using natural cubic splines. Both right‐ and interval‐censored data are considered. The suggested approach is applied on two types of family studies using the gamma‐ and stable frailty distribution: The first study is on adoption data where the association between survival in families of adopted children and their adoptive and biological parents is studied. The second study is a cross‐sectional study of the occurrence of back and neck pain in twins, illustrating the methodology in the context of genetic epidemiology. Copyright © 2010 John Wiley & Sons, Ltd.