共同方法变异是“致命瘟疫”吗?——论争、新知与应对

共同方法变异是由构念间相似的测量方法特征引起的系统变异, 可歪曲构念间的关系, 造成共同方法偏差。60年来, 这一问题在社会科学研究中被反复提及, 但它是否严重威胁研究效度尚无定论。虽然实证证据表明, 共同方法变异普遍存在, 数据来源、测量时间、问卷设计等因素可导致共同方法偏差, 使自我报告的横断式调查研究饱受质疑, 但部分学者从测量误差和非共同方法变异的制约作用等角度做出了回应和辩护, 认为无需过度担忧。以测量为中心的新视角强调共同方法变异是测量方法和被测构念交互作用的产物, 应从方法和构念两个维度评估共同方法变异风险。建议研究者树立均衡无偏的态度, 接纳共同方法变异的存在, 纠正对自我报告的偏见, 着重通过改进研究设计做好预先应对。     

应对行为跨文化测评的构念等同与偏差性研究

本文对COPE量表测评我国大学生应对行为方式的构念等同与偏差性进行深入探讨。采用验证性因素分析的方法测试了原版量表(COPE)及其中文修订本(C-COPE)的不同因素结构模型与465名大学生测评数据的拟合优度。研究结果支持C—COPE的测评维度结构,表明COPE量表对我国人群所进行的应对测评与西方社会的相比确实存在跨文化构念不等同性或偏差性,两者测评结果的跨文化比较因此缺乏必要前提条件。文中对所发生的构念偏差现象进行了详细分析。     

共同方法变异的影响及其统计控制途径的模型分析

共同方法变异(common method variance, CMV)指两个变量之间变异的重叠是因为使用同类测量工具而导致, 而不是代表潜在构念之间的真实关系。虽然以往研究显示CMV不一定导致研究结果的偏差, 在实际研究中应当加以考量。特别是在使用测量方法的研究中, 如果数据来源越单一, 测量方法越类似, CMV效应使研究结果产生偏差的可能性越大。CMV效应的控制方法包括过程控制法和统计控制法。在统计控制法的选择和使用上, 需要重点考虑该方法是否分离了三大变异(特质变异、方法变异和误差变异), CMV效应是在测量构念层面还是题目层面, CMV效应是加法效应还是乘法效应。控制潜在方法因子途径是统计控制方法中最重要的一类方法, 理解其模型是正确使用这类方法的前提。未来研究应当关注多个研究的CMV效应和侧重评估某个理论研究中CMV所引起的潜在的效度威胁。     

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。     

共同方法偏差的统计检验与控制方法

共同方法偏差是心理学研究中一个越来越被关注的课题,但国内心理学界对其的介绍、研究还比较少,导致研究中对共同方法偏差的控制还有所欠缺。共同方法偏差的控制方法分为程序控制和统计控制,该文介绍了共同方法偏差的多种统计控制法,如因素分析法、偏相关法、潜在的误差变量控制法、结构方程模型法等,分析了其各自的优缺点,并提出了如何选择采用这些方法的建议.     

评价中心测评的评分误差分析研究

本研究应用概化理论对评价中心中的评分误差控制问题进行了系统的分析探讨,得出了以下研究结论：(1)总体上,在评价中心(以LGD为例)测评中,评价员对研究设计的测评维度的评分基本反映了被试的真实能力水平,测量误差较小;(2)评价员对合作能力、应变能力和总体印象等维度的评价标准的理解具有较高的一致性,但对决策能力等维度的评价标准的理解存在一定的偏差;(3)在评价中心(以LGD为例)测评中,采用4名评价员能达到预期的测量目标,符合测评应用的经济性、有效性原则。     

视觉观点采择中自我中心性偏差的抑制和归因之争

自我中心性偏差是社交失败的重要原因,但其产生机制还存在争议。以往研究存在抑制性选择模型与流利性错误归因两种理论观点:前者认为对自身观点的抑制失败会导致自我中心性偏差;后者则认为错误地选择自身更为流畅的信息会导致自我中心性偏差。为整合上述争论,提出抑制-归因协同作用模型,认为抑制和归因两种加工或可共同导致自我中心性偏差。未来研究应借助精巧的研究范式和特殊被试群体,进一步验证该模型。     

任务类型与信息清晰度对社会比较中认知偏差的影响

社会比较中的认知偏差是指个体在社会比较中表现出的过度自信与不自信现象.本研究在前人研究的基础之上,以在校大学生为被试,采用两个系列实验,探讨了社会比较中认知偏差现象的原因以及对判断和决策的影响.研究结果发现:在社会比较中,面对不同类型的问题,会出现不同的认知偏差;在社会比较中,不同类型的问题和信息清晰度共同影响认知偏差,且二者之间存在交互作用;社会比较中的认知偏差会影响个体的决策意图.     

因素分析在测评表项目分析中的应用

结合理论设想和实验研究,探讨了因素分析应用于测评法项目分析的可能性,发现对测评者进行 Q 型因素分析,既能作为分析项目的手段,为设计和修改项目提供信息,也能分析测评的情况,发现与之有关的偏差。同时也指出,只有将因素分析的数据与实况访谈相结合,才是实现上述设想的有效途径。     

共同方法偏差检验：问题与建议

检验共同方法偏差(CMB)已经成为心理学实证研究中的一个环节。本文从数学模型角度分析方法变异(CMV)的影响,并讨论了CMB常用的检验法——Harman单因子法、控制未测量的潜在方法因子(ULMC)法、验证性因子分析(CFA)标签变量法的检验力。Harman单因子法检验力很低,ULMC法检验力中等,CFA标签变量法检验力虽然较高但问题也不少。提出一个好的检验法应当满足的三个特点：符合CMV的数学模型、评价标准不受非CMV来源的影响、对CMV、CMB的变化敏感。最后给出CMB检验的建议。     

A Meta‐Analytic Multitrait Multirater Separation of Substance and Style in Social Desirability Scales

Though unlikely virtues scales have a long history in personality, clinical, and applied psychology for detecting socially desirable responding, using such social desirability (SD) scales has generally failed to improve the validity of personality measures. We examined whether this is because (a) response distortion itself has minimal impact on personality's validity, (b) SD scales are ineffective at assessing response distortion, or (c) SD scales are conflated with substantive trait variance. We compiled a meta‐analytic multitrait multimethod matrix consisting of multirater personality traits, SD scales, and performance outcomes. We examined the influence of trait factors and self‐report method factors on SD scales and performance. We found that self‐report method variance (a) was negatively related to performance, (b) would suppress personality‐performance relationships for self‐report measures, and (c) was (partially) assessed by SD scales. However, relative to the effects of self‐report method variance, SD scales are even more strongly influenced by Conscientiousness, Emotional Stability, and Agreeableness. It is not the case that SD scales are insensitive to inflated responding but that their susceptibility to personality trait variance likely outweighs their benefits. We discuss the implications of these results for using SD scales in research and practice.     

Method Variance in Organizational Behavior and Human Resources Research: Effects on Correlations,Path Coefficients,and Hypothesis Testing

This research simulates the effects of method variance on correlations, standardized regression (path) coefficients, and squared multiple correlation coefficients. The results show that method variance can have extreme effects on these measures of association, depending on assumptions made about the nature of the method factors. The analysis also indicated that method variance can have strong effects on the probability of obtaining significant findings in the absence of true relationships. The link between findings of the present study and current developments on method variance in organizational behavior and human resources management research is discussed.     

Commentary: The role of intrapersonal psychological variables in academic school learning

Intellectual abilities may contribute up to 25% of the variance in measures of academic school learning. However, the role of intrapersonal variables other than cognitive ability (personality traits, motivational dynamic factors, transitory emotional states) has usually been considered as fairly trivial. Past research, to the contrary, suggests that under stressful conditions, the relative contribution of such intrapersonal factors may even become predominant in influencing achievement. When analyses are based on change scores rather than single-occasion measures (which include trait contamination variance), the influence of emotional states on learning is shown to be very significant indeed.     

The Other Side of Method Bias: The Perils of Distinct Source Research Designs

Common source bias has been the focus of much attention. To minimize the problem, researchers have sometimes been advised to take measurements of predictors from one observer and measurements of outcomes from another observer or to use separate occasions of measurement. We propose that these efforts to eliminate biases due to common source variance create serious problems. To demonstrate the problems of using what we term the “distinct sources” measurement design, we provide an integrative review of the literature regarding both contamination and deficiency of measures. Building on this theme, the article uses simulated data to demonstrate how using data from distinct observers or occasions of measurement can distort estimates of predictor importance at least as much as common source variance. Alternative multisource designs are advocated and examined for tractability by simulating various numbers of observations and sources in the research design.     

Trait configurations in self-managed teams: a conceptual examination of the use of seeding for maximizing and minimizing trait variance in teams

In this article, the authors argue that there is no one best way to make placement decisions on self-managed teams. Drawing from theories of supplementary and complementary fit, they develop a conceptual model that suggests that (a) maximization principles should be applied to extroversion variance (i.e., complementary fit), (b) minimization principles should be applied to conscientiousness variance (i.e., supplementary fit), and (c) extroversion variance and conscientiousness variance interact to influence team performance. They also argue that previous research has underestimated the effect of extroversion and conscientiousness variance on performance because of suboptimal design. The authors, therefore, present an alternative method for making team placement decisions (i.e., seeding) that can be used to maximize or minimize variance in teams.     

A methodological note on ordered Q-Sort ratings

Patterns of ratings using the Q-Sort method and the Likert-type method are compared. Ordering effects are found in Q-Sort ratings that are not present in Likert-type ratings. Specifically, item order is related to both item variance and item placement, such that items appearing near the end of the Q-Sort have less variance and more central placement. This finding is verified across three measures in several datasets spanning nearly 20 years of research. Such item order effects appear to attenuate average absolute relationships (covariances and correlations) between items appearing near the end of the Q-Sort and other measures. Randomization of items may be (in some situations) a viable course of action to minimize these effects at a sample level.     

A META-ANALTTIC REVIEW OF ATTITUDINAL AND DISPOSITIONAL PREDICTORS OF ORGANIZATIONAL CITIZENSHIP BEHAVIOR

A quantitative review of 55 studies supports the conclusion that job attitudes are robust predictors of organizational citizenship behavior (OCB). The relationship between job satisfaction and OCB is stronger than that between satisfaction and in-role performance, at least among nonmanagerial and nonprofessional groups. Other attitudinal measures (perceived fairness, organizational commitment, leader supportiveness) correlate with OCB at roughly the same level as satisfaction. Dispositional measures do not correlate nearly as well with OCB (with the exception of conscientiousness). The most notable moderator of these correlations appears to be the use of self- versus other-rating of OCB; self-ratings are associated with higher correlations, suggesting spurious inflation due to common method variance, and much greater variance in correlation. Differences in subject groups and work settings do not account for much variance in the relationships. Implications are noted for theory, practice, and strategies for future research on OCB.     

Genetic and Environmental Influences on Personality: A Study of Twins Reared Together Using the Self- and Peer Report NEO-FFI Scales

ABSTRACT Previous behavior-genetic research on personality has been almost exclusively based on self-report questionnaire measures. The purpose of this research was to measure personality constructs via self- and peer reports on the items of the NEO Five-Factor Inventory (Costa & McCrae, 1989). The sample included 660 monozygotic and 200 same sex and 104 opposite sex dizygotic twin pairs. We collected self- and two independent peer reports for each of the twins. Our analysis of self-report data replicates earlier findings of a substantial genetic influence on the Big Five (h²= .42 to .56). We also found this influence for peer reports. Our results validate findings based solely on self-reports. However, estimates of genetic contributions to phenotypic variance were substantially higher when based on peer reports (h²= .51 to .81) or self- and peer reports (h²= .66 to .79) because these data allowed us to separate error variance from variance due to nonshared environmental in-fluences. Correlations between self- and peer reports reflected the same genetic influences to a much higher extent than identical environmental effects.