测量等价性的概念及其判定条件

测量等价性指的是,应用量表进行测量时,当观测变量和潜在特质之间的关系在相比较的各个组之间等同时,就称该量表具备测量等价性。特别地,来自不同群体但在潜在特质上得分相等的个体,他们观测变量的得分也应该相等。测量工具满足测量等价性的要求是进行组间差异比较的前提条件。该文首先明确了测量等价性的概念及其研究历史,然后阐述了测量等价性的重要性以及对测量等价性分析的必要性,进而讨论了在结构方程模型中测量等价性所要满足的5个条件,最后列举了模型优劣判定的拟合度指数     

二阶因素模型的测量等价性检验——以大学生网络利他行为量表为例

与一阶因素模型相比,二阶因素模型具有较多优点,但二阶因素模型的测量等价性检验要更复杂,它需要依次进行七个不同水平的检验：形等价、一阶弱等价、二阶弱等价、一阶强等价、二阶强等价、二阶严等价和一阶严等价。低水平的等价性满足之后,才能进行更为严格的高一水平的等价性检验。运用均值和协方差结构（MACS）模型对大学生网络利他行为量表（IABSU）进行二阶因素模型的测量等价性检验,结果表明,IABSU具有跨地域的完全一阶、二阶严等价性。     

分类数据测量等价性检验方法及其比较：项目阈值(难度)参数的组间差异性检验

测量工具满足等价性是进行多组比较的前提, 测量等价性的检验方法主要有基于CFA的多组比较法和基于IRT的DIF检验两类方法。文章比较了单维测验情境下基于CCFA的DIFFTEST检验方法和基于IRT模型的IRT-LR检验方法, 以及多维测验情境下DIFFTEST和基于MIRT的卡方检验方法的差异。通过模拟研究的方法, 比较了几种方法的检验力和第一类错误, 并考虑了样本总量、样本量的组间均衡性、测验长度、阈值差异大小以及维度间相关程度的影响。研究结果表明：(1)在单维测验下, IRT-LR是比DIFFTEST更为严格的检验方法; 多维测验下, 在测验较长、测验维度之间相关较高时, MIRT-MG比DIFFTEST更容易检验出项目阈值的差异, 而在测验长度较短、维度之间相关较小时, DIFFTEST的检验力反而略高于MIRT-MG方法。(2)随着阈值差值增加, DIFFTEST、IRT-LR和MIRT-MG三种方法的检验力均在增加, 当阈值差异达到中等或较大时, 三种方法都可以有效检验出测验阈值的不等价性。(3)随着样本总量增加, DIFFTEST、IRT-LR和MIRT-MG方法的检验力均在增加; 在总样本量不变, 两组样本均衡情况下三种方法的检验力均高于不均衡的情况。(4)违背等价性题目个数不变时, 测验越长DIFFTEST的检验力会下降, 而IRT-LR和MIRT-MG检验力则上升。(5) DIFFTEST方法的一类错误率平均值接近名义值0.05; 而IRT-LR和MIRT-MG方法的一类错误率平均值远低于0.05。     

多维自我概念量表的测量等价性检验

运用MSCS测量923名中国中学生自我概念,探查MSCS的跨组测量等价性。结果显示,MSCS具有跨性别、学校、城乡的严等价性。研究表明,MSCS是一个适应广泛的量表,可以基于观察数据进行跨性别、学校、城乡的平均数比较和方差齐性检验。     

道德差异与人的不可侵犯性

后果主义者认为,一项选择(包括作为和不作为)的道德重要性取决于它所产生的后果,因此不同类型的选择之间并没有内在的道德重要性差异,这被称为后果主义的等价性观点.义务论者卡姆对这一观点提出了批评,她认为不同类型的道德选择之间存在着道德重要性上的差异,这一差异对后果主义的道德要求构成了义务论约束,使得行为者至少在某些情形下不应当实行某个行为,即使这个行为能够产生后果主义者所认为的最好后果.卡姆进而通过诉诸人的不可侵犯性来对道德差异进行辩护.     

严谨性的结构及其应用研究述评

严谨性(Conscientiousness)是指个体在按照社会规范的要求控制冲动的倾向、以任务和目标为导向、先思后行、延迟满足以及遵守规范和纪律等方面上的个体差异。由于其在应用心理学领域(如, 组织管理心理学)的重要作用而被广泛而深入的研究, 主要内容涉及严谨性对工作绩效和其他工作相关行为的的预测、对健康行为和寿命的预测、对学业表现的预测等方面。文章全面回顾了近年来严谨性的结构及其在管理、教育和健康领域的相关研究, 并指出将来的研究应进一步深入探索严谨性的次级结构、测量工具的编制、严谨性与绩效间关系的假设、严谨性与寿命和健康行为之间的关系等问题。     

乌特勒支恋家症量表在大学生中的信效度检验

为检验中文版乌特勒支恋家症量表在大学生群体中的信效度,使用样本1(n=1071),进行信效度检验与测量等值性,使用样本2(n=177,连续5期)检验跨时点的纵向测量等值性。结果表明中文版乌特勒支恋家症量表为五因子结构,包含想家、孤独、想念朋友、适应困难和关于家庭的沉思5个维度,具有良好的信效度、效标效度与测量等值性。意味该量表适合在我国大学生群体中使用,并能够用于跨性别、年级以及时点的相关研究。     

个体依恋特征的二重性：特质性依恋与状态性依恋

传统依恋理论认为个体依恋心理和行为模式具有相对稳定性, 但无论在信息加工还是个体发展过程中, 个体依恋模式均表现出二重性, 即既具有相对稳定性, 又具有情境敏感性。个体在情境中所表现出的依恋模式是个体相对稳定的特质性依恋和情境特征相互作用的结果。依恋启动研究中特质性依恋特征与依恋启动效应之间的交互作用模式为理解依恋二重特征及其关系提供了窗口。依恋系统激活的两阶段模型为整合和解释这些相互作用模式提供了框架。未来研究应优化依恋二重特征关系研究中启动效应的操作检验, 考虑依恋焦虑和回避维度的交互作用, 关注高焦虑群体内的依恋差异, 以理析依恋二重特征之间的相互作用方式, 同时关注依恋策略影响依恋启动效应的时间进程, 探究依恋二重特征相互作用的机制。     

形成性测量模型：结构方程模型的新视角

形成性测量模型(Formative Model, FM)是指标变异导致潜变量变异的模型, 反映性测量模型(Reflective Model, RM)是潜变量变异导致指标变异的模型。FM在模型界定、识别和估计、信效度评价以及模型应用等方面均与RM存在极大的不同。模型界定错误会使参数估计发生偏差, 影响统计结论的有效性, 应当审慎考虑指标和潜变量之间的关系, 选择恰当的测量模型。进一步揭示两者的区别和误用带来的偏差, 完善FM的识别和估计、信效度评价方法、对变量含义的解释以及高阶FM的理论解释和模型估计是未来的研究方向。     

气质性乐观与心理健康关系的元分析

运用元分析方法分别探讨了气质性乐观与心理健康的积极指标和消极指标的关系。共有106项研究满足了元分析的标准,涉及气质性乐观与心理健康积极指标的研究有70项,包括83个独立样本(N=30627);涉及气质性乐观与心理健康消极指标的研究有75项,包括105个独立样本(N=39064)。元分析结果发现:(1)整体上气质性乐观与心理健康积极指标有显著正相关(r=0.41),与心理健康消极指标有显著负相关(r=-0.41)。(2)气质性乐观与不同心理健康指标的相关有显著差异,积极指标中,与自尊的相关最高;消极指标中,与抑郁的相关最高。(3)气质性乐观测量工具的差异对其与心理健康的关系没有显著影响。(4)不同年龄阶段群体中气质性乐观与心理健康的关系没有显著差异。(5)文化背景差异对两者的关系有显著影响,西方文化中气质性乐观与心理健康的相关高于东方文化中的相关。     

Bias and equivalence in cross-cultural assessment: an overview

In every cross-cultural study, the question as to whether test scores obtained in different cultural populations can be interpreted in the same way across these populations has to be dealt with. Bias and equivalence have become the common terms to refer to the issue. Taxonomy of both bias and equivalence is presented. Bias can be engendered by the theoretical construct (construct bias), the method such as the form of test administration (method bias), and the item content (item bias). Equivalence refers to the measurement level at which scores can be compared across cultures. Three levels of equivalence are possible: the same construct is measured in each cultural group but the functional form of the relationship between scores obtained in various groups is unknown (structural equivalence), scores have the same measurement unit across populations but have different origins (measurement unit equivalence), and scores have the same measurement unit and origin in all populations (full scale equivalence). The most frequently encountered sources of bias and their remedies are described.     

等效性检验——结构方程模型评价和测量不变性分析的新视角

常用的结构方程模型拟合指数存在一定局限, 如χ ²以传统零假设为目标假设, 无法验证模型, 而RMSEA和CFI等描述性的拟合指数不具备推断统计性质, 等效性检验有效弥补了这些问题。首先说明等效性检验如何评价单个模型的拟合, 并解释其与零假设检验的不同, 然后介绍等效性检验如何分析测量不变性, 接着用实证数据展示了等效性检验在单个模型评价和测量不变性检验中的效果, 并与传统模型评价方法比较。     

Group Differences in Regression Intercepts: Implications for Factorial Invariance

Studies of differential prediction typically examine group differences in linear regression slopes or intercepts for predicting criterion scores from one or more test scores. When there are no group differences in slopes, what are the implications of differences in regression intercepts for the measurement equivalence of the tests or criterion across groups? Measurement equivalence is here defined as factorial invariance under a single-factor model for the tests and criterion. Two theorems are given that describe conditions under which intercept differences can exist under factorial invariance. In such cases, intercept differences do not result from measurement bias in either the tests or criterion. The conditions of the theorems are testable using multiple-group confirmatory factor analysis. These test procedures are illustrated in real data. The implications of the theorems and the test procedures for studies of differential prediction are discussed.     

The Five Factor Model in personnel selection: Measurement equivalence between applicant and non-applicant groups

This study investigates the measurement equivalence of a Five Factor measure of personality between applicant and non-applicant samples. The Big Five Questionnaire-2 was administered in two samples: A group of volunteers (n = 903), who completed the test for research purposes, and a group applying for jobs, who completed the test during hiring procedures (n = 401). Multiple-group confirmatory factor analysis on item composites was conducted to test for the equivalence of factor covariance and mean structures of twenty facets of the Five Factors. Item-level analyses were carried out through analysis of variance to further examine the issue of measurement invariance. Findings suggested that personality facets have the same measurement unit across applicants and non-applicants, while a lack of equivalence was found in the origin of the scales. Similar results were found at the item-level. Implications for personality assessment are advanced and discussed.     

网络测验和纸笔测验的测量不变性研究：以生活满意度量表为例

以生活满意度量表为例,运用实证性因素分析,考察在中国文化下网络测验和传统纸笔测验之间的测量不变性。结果显示,网络测验和纸笔测验之间存在弱不变性,即网络测验和纸笔测验有着相同的测量单位;但网络测验和纸笔测验只存在部分的强不变性和部分的严格不变性,测验实施环境对结果的影响不可忽视。该研究表明,恰当设计的网络测验是可靠的,同时还提示,当一个测验在不同情境下运用时,检验测量不变性十分必要     

Evaluating the Psychometric and Measurement Characteristics of a Measure of Sexual Orientation Harassment

We use classical test theory (CTT) and item response theory (IRT) methodologies to examine the psychometric and measurement properties of an instrument designed to assess sexual orientation harassment among military personnel (N?=?71,989). CTT analyses indicated that items were unidimensional and exhibited adequate levels of reliability. IRT analyses demonstrated that the items functioned similarly and exhibited appropriate levels of item discrimination. However, the analyses also suggested that the sensitivity of the items may be limited. Differential test functioning analyses provided evidence of the measurement equivalence of the instrument across male and female respondents. The findings provide support for the psychometric properties and measurement equivalence of the instrument for measuring sexual orientation harassment among male and female military personnel. We discuss the implications of our findings for future research on sexual orientation harassment in the workplace.     

Paper-and-pencil and web-based testing: the measurement invariance of the Big Five personality tests in applied settings

This study investigates the measurement equivalence of a five-factor measure of personality across two groups applying for jobs, who completed the same questionnaire using either a paper-and-pencil (n = 429) or a web online answer format (n = 651). The data were collected using the Big Five Questionnaire-2 (BFQ-2; which is a measure of the Five Factor Model) of personality traits. Multiple-group confirmatory factor analysis was used to test for the equivalence of factor covariance and mean structures of the BFQ-2. Findings suggested that the Five Factor Model scales have the same measurement unit and origin across applicants using different administration modes. However, latent means were slightly higher for applicants who responded in a web and unproctored condition than for applicants who completed a paper-and-pencil version of the same test. Practical implications for personality assessment are discussed.     

Measurement Equivalence Between Applicant and Incumbent Groups: An IRT Analysis of Personality Scales

Incumbents are often used in the development and validation of a wide variety of personnel selection instruments, including noncognitive instruments such as personality tests. However, the degree to which assumed motivational factors impact the measurement equivalence and validity of tests developed using incumbents has not been adequately addressed. This study addressed this issue by examining the measurement equivalence of 6 personality scales between a group applying for jobs as sales managers in a large retail organization (N = 999) and a group of sales managers currently employed in that organization (N = 796). A graded item response theory model (Samejima, 1969) was fit to the personality scales in each group. Results indicated that moderately large differences existed in personality scale scores (approximately 1/2 standard deviation units) but only one of the six scales contained any items that evidenced differential item functioning and no scales evidenced differential test functioning. In addition, person-level analyses showed no apparent differences across groups in aberrant responding. The results suggest that personality measures used for selection retain similar psychometric properties to those used in incumbent validation studies.