贝叶斯多组比较——渐近测量不变性

在行为科学研究领域中,检验测量工具的测量不变性是进行群体差异比较的前提。目前,多组验证性因子分析(多组CFA)方法被广泛用于检验测量不变性,但是它对跨组等值的限制过于严格,在实际应用中常常存在大量局限。贝叶斯渐近测量不变性方法基于贝叶斯思想的优良特性,放宽了传统多组CFA方法对跨组差异的严格限制,避免了传统方法的问题,具有较高的应用价值。文章详细介绍了贝叶斯渐近测量不变性方法的原理及优势,同时通过实例展示了渐近测量不变性方法在Mplus软件中的具体分析过程。     

Doubly Robust-Type Estimation for Covariate Adjustment in Latent Variable Modeling

Due to the difficulty in achieving a random assignment, a quasi-experimental or observational study design is frequently used in the behavioral and social sciences. If a nonrandom assignment depends on the covariates, multiple group structural equation modeling, that includes the regression function of the dependent variables on the covariates that determine the assignment, can provide reasonable estimates under the condition of correct specification of the regression function. However, it is usually difficult to specify the correct regression function because the dimensions of the dependent variables and covariates are typically large. Therefore, the propensity score adjustment methods have been proposed, since they do not require the specification of the regression function and have been applied to several applied studies. However, these methods produce biased estimates if the assignment mechanism is incorrectly specified. In order to make a more robust inference, it would be more useful to develop an estimation method that integrates the regression approach with the propensity score methodology. In this study we propose a doubly robust-type estimation method for marginal multiple group structural equation modeling. This method provides a consistent estimator if either the regression function or the assignment mechanism is correctly specified. A simulation study indicates that the proposed estimation method is more robust than the existing methods. This research was partially supported by the Ministry of Education, Science, Sports and Culture, Grant-in-Aid for Young Scientists (B), 187-30406.     

Measurement Invariance,Predictive Invariance,and the Duality Paradox

The statistical literature on bias in psychological testing distinguishes at least two forms of bias: measurement bias and predictive bias. Measurement bias concerns group differences in the relationship between a test and the latent variable to be measured. Predictive bias concerns group differences in the relationship between a test and an external criterion. How are these two forms of bias related? For example. if a test is unbiased in the predictive sense, does this fact support the hypothesis that the test is unbiased in the measurement sense? A theorem is given that describes the conditions under which measurement invariance (lack of bias) is consistent with predictive invariance for the linear case. Paradoxically, these two forms of invariance are shown to be inconsistent under realistic conditions. This duality or inconsistency is illustrated in simulated data. The implications of the duality for group differences research are illustrated in real data involving gender and ethnic differences on the SAT. The phenomenon of duality may force a reinterpretation of common empirical findings of test criterion regression slope invariance. and of invariance in test validities. Other implications are discussed.     

Invariance in Measurement and Prediction Revisited

Borsboom (Psychometrika, 71:425–440, 2006) noted that recent work on measurement invariance (MI) and predictive invariance (PI) has had little impact on the practice of measurement in psychology. To understand this contention, the definitions of MI and PI are reviewed, followed by results on the consistency between the two forms of invariance in the general case. The special parametric cases of factor analysis (strict factorial invariance) and linear regression analyses (strong regression invariance) are then described, along with findings on the inconsistency between the two forms of invariance in this context. Two numerical examples of inconsistency are reviewed in detail. The impact of violations of MI on accuracy of selection is illustrated. Finally, reasons for the slow dissemination of work on invariance are discussed, and the prospects for altering this situation are weighed. This paper is based on the Presidential Address given at the International Meeting of the Psychometric Society in Tokyo, Japan, on July 11, 2007. This research was supported by National Institute of Mental Health grants 1P30 MH 068685-01A1 and RO1 MH64707-01.     

Testing for Measurement Invariance with Respect to an Ordinal Variable

Researchers are often interested in testing for measurement invariance with respect to an ordinal auxiliary variable such as age group, income class, or school grade. In a factor-analytic context, these tests are traditionally carried out via a likelihood ratio test statistic comparing a model where parameters differ across groups to a model where parameters are equal across groups. This test neglects the fact that the auxiliary variable is ordinal, and it is also known to be overly sensitive at large sample sizes. In this paper, we propose test statistics that explicitly account for the ordinality of the auxiliary variable, resulting in higher power against “monotonic” violations of measurement invariance and lower power against “non-monotonic” ones. The statistics are derived from a family of tests based on stochastic processes that have recently received attention in the psychometric literature. The statistics are illustrated via an application involving real data, and their performance is studied via simulation.     

Structure and Measurement Invariance of Adult Romantic Attachment

Romantic attachment is a popular theory for explaining affect, cognition, and behavior in romantic contexts. This popularity has led to a surge of self-report measures assessing dimensions of attachment. In this study, we considered the ability of 2 common attachment measures, the Adult Attachment Questionnaire (AAQ) and the Experience in Close Relationships–Revised (ECR–R), to replicate the avoidant and anxious attachment factors. We also determined the degree of measurement invariance across, and mean differences between, genders and single and nonsingle individuals. Both the AAQ (N = 650) and the ECR–R (N = 1,271) successfully distinguished avoidant and attachment factors. The AAQ showed evidence for partial strong measurement invariance, whereas the ECR-R showed strict factorial invariance for both gender and relationship status. Gender differences were detected on both measures in a direction consistent with previous research, with males exhibiting higher levels of avoidant attachment (relative to females) and females exhibiting higher levels of anxious attachment (relative to males). Furthermore, when compared to individuals who were currently single, those in romantic relationships exhibited lower levels of avoidant tendencies. This research aligns with the notion that the AAQ and ECR–R reliably assess similar constructs, across genders and single and nonsingle individuals.     

Effects of Variation and Prior Knowledge on Abstract Concept Learning

Learning abstract concepts through concrete examples may promote learning at the cost of inhibiting transfer. The present study investigated one approach to solving this problem: systematically varying superficial features of the examples. Participants learned to solve problems involving a mathematical concept by studying either superficially similar or varied examples. In Experiment 1, less knowledgeable participants learned better from similar examples, while more knowledgeable participants learned better from varied examples. In Experiment 2, prior to learning how to solve the problems, some participants received a pretraining aimed at increasing attention to the structural relations underlying the target concept. These participants, like the more knowledgeable participants in Experiment 1, learned better from varied examples. Thus, the utility of varied examples depends on prior knowledge and, in particular, ability to attend to relevant structure. Increasing this ability can prepare learners to learn more effectively from varied examples.     

Self-Other Differentiation Scale: Dimensionality,IRT Parameterization,and Measurement Invariance

The Self-Other Differentiation Scale (Olver, Aries, &; Batgos, 1989 Olver, R. R., Aries, E., &; Batgos, J. (1989). Self-other differentiation and the mother-child relationship: The effects of sex and birth order. The Journal of Genetic Psychology, 150, 311–321. doi:10.1080/00221325.1989.9914600[Taylor &; Francis Online] , [Google Scholar]) is a self-report instrument assessing the experience of a separate sense of self from others. The authors aimed to examine its dimensionality, reliability, and measurement invariance across gender. It was completed by 348 participants (48% men) from 17 to 30 years old in Study 1, 348 participants (40% men) from 18 to 28 years old in Study 2, and 1,068 participants (49% men) from 17 to 28 years old in Study 3. The results supported the hypothesis of just one factor underlying the scale; they also showed an appropriate internal consistency and a partial measurement invariance across gender. Results also showed evidence for a 10-item version of the scale. Globally, the Self-Other Differentiation Scale can be considered a good scale to assess individual's sense of differentiation of one's own sense of self from others.     

Tests of Measurement Invariance Without Subgroups: A Generalization of Classical Methods

The issue of measurement invariance commonly arises in factor-analytic contexts, with methods for assessment including likelihood ratio tests, Lagrange multiplier tests, and Wald tests. These tests all require advance definition of the number of groups, group membership, and offending model parameters. In this paper, we study tests of measurement invariance based on stochastic processes of casewise derivatives of the likelihood function. These tests can be viewed as generalizations of the Lagrange multiplier test, and they are especially useful for: (i) identifying subgroups of individuals that violate measurement invariance along a continuous auxiliary variable without prespecified thresholds, and (ii) identifying specific parameters impacted by measurement invariance violations. The tests are presented and illustrated in detail, including an application to a study of stereotype threat and simulations examining the tests’ abilities in controlled conditions.     

Consequences of Ignoring Guessing Effects on Measurement Invariance Analysis

Pseudo-guessing parameters are present in item response theory applications for many educational assessments. When sample size is not sufficiently large, the guessing parameters may be ignored from the analysis. This study examines the impact of ignoring pseudo-guessing parameters on measurement invariance analysis, specifically, on item difficulty, item discrimination, and mean and variance of ability distribution. Results show that when non-zero guessing parameters are ignored from the measurement invariance analysis, item discrimination estimates tend to decrease particularly for more difficult items, and item difficulty estimates decrease unless the items are highly discriminating and difficult. As the guessing parameter increases, the size of the decrease in item discrimination and difficulty tends to increase, and the estimated mean and variance of ability distribution tend to be inaccurate. When two groups have heterogeneous ability distributions, ignoring the guessing parameter affects the reference group and the focal group differently. Implications of result findings are discussed.     

心理测量平衡性研究与实例

心理测量研究中,测量不变性(或称平衡性)是量表稳定性问题中的一个难题而且在比较研究中受到特别重视。结构方程模型因在平衡性形式捕捉方面功能强大而受到广泛应用。该研究讨论了测量平衡性的各种形式并演示了应用结构方程模型评估测量平衡性的过程。     

Factorial Structure and Measurement Invariance of the Innovative Behavior Questionnaire

The article presents an analysis of the factorial structure and measurement invariance of the Innovative Behavior Questionnaire, developed by Scott and Bruce. Although the instrument is widely used to capture individuals' innovative behavior, very little evidence concerning its psychometric properties is available. A time‐lagged study among 382 employees was conducted to check the factorial structure of the questionnaire, using confirmatory factor analysis, as well as its measurement invariance across gender and time. One‐factor structure (with correlated error terms of first three items) and strict invariance across time and across gender of the Innovative Behavior Questionnaire were demonstrated. As such, the measure can be used as a reliable tool for capturing individuals' innovative behavior by self‐report.     

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     

Measurement Invariance of the Day Reconstruction Method: Results from the COURAGE in Europe Project

Given the growing interest in the study of subjective well-being as a measure of social progress, instruments that produce valid and reliable scores and that can be used within and across countries are needed. The aim of the present study was to analyze the measurement equivalence of the Day Reconstruction Method in its brief version, using nationally representative samples from Finland, Poland, and Spain obtained within the COURAGE in Europe project. The goodness-of-fit of a two-correlated-factors model and the reliability of the scores obtained were assessed. Cross-country invariance was tested employing a multiple group confirmatory factor analysis, through sequential constraint imposition. In each country, measurement invariance was tested across time frames (morning, afternoon and evening) and days of the week (weekday and weekend). The results found support for the hypothesis of a two-correlated-factors (positive and negative affect) structure; the reliability of the positive, the negative and the net affect scores showed appropriate values. A high equivalence across the three national samples was found: all items except one showed strong measurement invariance indicating that respondents from Finland, Poland, and Spain attribute the same meaning to the latent construct under study, and the levels of the underlying items are equal in all three countries. Similar results were found for the measurement equivalence across time frames and days of the week. Our findings support the assumption of comparability across the different samples considered; in general, higher positive affect and lower negative affect were found in Finland, in the evening and at the weekend.     

Null Results in Assessing Survey Score Comparability: Illustrating Measurement Invariance Using Item Response Theory

In using organizational surveys for decision-making, it is essential to consider measurement equivalence/invariance (ME/I), which addresses the questions of whether score differences are attributable to differences in the latent variable we intend to measure, or attributable to confounding differences in measurement properties. Due to the tendency for null results to remain unpublished, most articles have focused on findings of, and reasons for violations of ME/I. On the other hand, little is available to practitioners and researchers concerning situations where ME/I can be expected to uphold. This is especially disconcerting due to the fact that the null is the desired result in such analyses, and allows for unfettered observed-score comparisons. This special issue presents a unique opportunity to provide such a discussion using real-world examples from an organizational culture survey. In doing so we hope to clear up confusion surrounding the concept of ME/I, when it can be expected, and how it relates to actual differences in scores. First, we review the basic tenets and past findings focusing on ME/I, and discuss the item response theory differential item functioning framework used here. Next, we show ME/I being upheld using organizational survey data wherein violations of ME/I would reasonably not be expected (i.e., the null hypothesis was predicted and supported), and simulate the consequences of ignoring ME/I. Finally, we suggest a set of conditions wherein ME/I is likely to be upheld.