The Problem with Having Two Watches: Assessment of Fit When RMSEA and CFI Disagree

The root mean square error of approximation (RMSEA) and the comparative fit index (CFI) are two widely applied indices to assess fit of structural equation models. Because these two indices are viewed positively by researchers, one might presume that their values would yield comparable qualitative assessments of model fit for any data set. When RMSEA and CFI offer different evaluations of model fit, we argue that researchers are likely to be confused and potentially make incorrect research conclusions. We derive the necessary as well as the sufficient conditions for inconsistent interpretations of these indices. We also study inconsistency in results for RMSEA and CFI at the sample level. Rather than indicating that the model is misspecified in a particular manner or that there are any flaws in the data, the two indices can disagree because (a) they evaluate, by design, the magnitude of the model's fit function value from different perspectives; (b) the cutoff values for these indices are arbitrary; and (c) the meaning of “good” fit and its relationship with fit indices are not well understood. In the context of inconsistent judgments of fit using RMSEA and CFI, we discuss the implications of using cutoff values to evaluate model fit in practice and to design SEM studies.     

When Suspicious Minds Go Political: Distrusting and Justifying the System at the Same Time

Drawing on the sensitivity to mean intentions model, we hypothesized that sensitivity to injustice from a victim's perspective (victim sensitivity) is negatively related to the acceptance of political reforms due to an inclination to attribute ulterior motives to policy makers. In Study 1 with a Canadian sample, initial evidence for this mediational model was obtained, as victim sensitivity uniquely predicted distrust of policy makers through general trait suspiciousness. In Study 2, victim‐sensitive Austrians and Germans ascribed sinister motives to initiators of an economic reform when contextual cues of initiators' untrustworthiness were given. This situational suspiciousness led them to subsequently oppose this particular reform, and it even generalized to the whole economic system by reducing economic‐system justification. However, in both studies, mutually suppressive tendencies toward both opposing and justifying the system occurred. This suggests that victim‐sensitive individuals may be torn between distrusting and endorsing the system because it can not only victimize but also promote a sense of security from victimization by conferring order.     

Comparative Analysis of Work Values Across Four Nations

Work values are important factors in career counseling and development. The purpose of this study was to test the measurement invariance of Terada's ( 2009 ) Vocational Values Inventory, as well as compare the means of 5 latent variables across 4 nations (Japan, South Korea, the United States, and Germany) using structural equation modeling. Results indicated that the assumptions of configural, metric, and intercept invariance were satisfied across the 4 nations. A comparison of the means of the 5 latent variables indicated that job security, an extrinsic work value, was perceived as the most important work value across the 4 nations.     

Regression away from the mean: Theory and examples

Using a standard repeated measures model with arbitrary true score distribution and normal error variables, we present some fundamental closed-form results which explicitly indicate the conditions under which regression effects towards (RTM) and away from the mean are expected. Specifically, we show that for skewed and bimodal distributions many or even most cases will show a regression effect that is in expectation away from the mean, or that is not just towards but actually beyond the mean. We illustrate our results in quantitative detail with typical examples from experimental and biometric applications, which exhibit a clear regression away from the mean (‘egression from the mean’) signature. We aim not to repeal cautionary advice against potential RTM effects, but to present a balanced view of regression effects, based on a clear identification of the conditions governing the form that regression effects take in repeated measures designs.     

论儒家伦理道德的普遍性与特殊性——以北宋理学家吕大临的思想的个案分析为例

本文试图以北宋理学家吕大临的思想的个案分析为例,探讨儒家伦理道德的普遍性与特殊性。文章通过对吕大临思想中的“性”、“仁”、“理义”、“天理”、“时中”等观念的解析,讨论了吕大临对儒家“道德法则”的普遍性和特殊性的看法以及他在处理两者之间关系方面的观点。     

Issues associated with repeated neuropsychological assessments

Distinguishing practice effects from other factors in repeated neuropsychological assessments are discussed in the context of research studies and clinical/forensic assessments. Potential methodological procedures for reducing the impact of practice effects in research settings are outlined. In contrast, the potential clinical utility and interpretation of practice effects in clinical assessments and forensic evaluations are highlighted.     

Approximate confidence intervals for a robust scale parameter

A recent paper by Wainer and Thissen has renewed the interest in Gini's mean difference,G, by pointing out its robust characteristics. This note presents distribution-free asymptotic confidence intervals for its population value,γ, in the one sample case and for the difference Δ=(γ ₁?γ ₂) in the two sample situations. Both procedures are based on a technique of jackknifingU-statistics developed by Arvesen.     

潜变量交互效应建模方法演变与简化

综述了近年来加入乘积指标的潜变量交互效应建模方法, 从产生乘积指标的策略、参数约束方法、均值结构与指标中心化的关系三个方面, 讨论了建模方法的简化进程。最后总结出同类方法中比较简洁又不失精确的潜变量交互效应建模方法—— 无需均值结构的无约束方法, 并给出了建模 步骤。     

Point-biserial correlation: Interval estimation,hypothesis testing,meta-analysis,and sample size determination

The point-biserial correlation is a commonly used measure of effect size in two-group designs. New estimators of point-biserial correlation are derived from different forms of a standardized mean difference. Point-biserial correlations are defined for designs with either fixed or random group sample sizes and can accommodate unequal variances. Confidence intervals and standard errors for the point-biserial correlation estimators are derived from the sampling distributions for pooled-variance and separate-variance versions of a standardized mean difference. The proposed point-biserial confidence intervals can be used to conduct directional two-sided tests, equivalence tests, directional non-equivalence tests, and non-inferiority tests. A confidence interval for an average point-biserial correlation in meta-analysis applications performs substantially better than the currently used methods. Sample size formulas for estimating a point-biserial correlation with desired precision and testing a point-biserial correlation with desired power are proposed. R functions are provided that can be used to compute the proposed confidence intervals and sample size formulas.