仿真模拟测评技术信度和效度的初步研究

本研究对典型的仿真测评技术——“角色扮演”测评方法的评分者信度、重测信度和效标关联效度进行了初步研究。结果表明：仿真模拟测评技术具有较强的岗位针对性,在相似情境中具有较高的预测效度,在某些要素上具有测评和培训的双重功能。     

心理测验在人才测评中的应用

本文探讨了心理测验在人才测评中应用价值和存在的问题,讨论了科学的人才测评与心理测验的关系,期望可以科学的把心理测验应用到人才测评工作中,提高人才测评的有效性和可靠性。     

基于胜任特征的人才测评

该文总结了国内外有关胜任特征与测评方面的文献,阐述了胜任特征作为人才测评的标准的内涵,进而总结了胜任特征应用于人才测评的作用与意义,最后简要介绍了基于胜任特征的人才测评的技术方法。本文有助于胜任特征与人才测评课题的进一步研究,对于人才测评的实践具有很强的指导意义。     

个性测验研制报告

本研究所编制的个性测验是根据我国企业人才素质测评需要而设计的,它包含有一个效度量表(掩饰性)和15项个性测评要素：自信心、责任心、自律性、进取性、合群性、灵活性、自主性、支配性、客观性、外向性、情绪性、宽容性、坚韧性、成就性、内外控。项目分析和信度、效度分析结果显示,该测验是可靠而有效的。     

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。     

试论我国人才测评事业的发展

本文在简要回顾西方人才测评发展历史的基础上,对我国人才测评事业的发展过程进行分析,提出三个不同的发展阶段及其特点。最后在总结经验的基础上,指出我国人才测评事业发展中存在的问题并提出建议。     

不同类型的测评维度对评价中心结构效度的影响研究

本研究将测评维度分为行为能力和心理特质两组,考察对评价中心结构效度的不同影响。A公司216名部门副经理级员工接受了本次管理素质评价中心测评,采用公文筐、角色扮演和无领导小组讨论三种方法,测查行为能力和心理特质两组维度,各自有三个维度被一种以上的方法测量。多质多法和验证性因素分析的结果表明,评价中心以行为能力比以心理特质为测评维度结构效度好;以行为能力为测评维度时,会聚效度和区分效度都较好。     

心理测评在我国人力资源服务中的应用现状及其存在的问题

心理测评是人才测评的重要组成部分和主要手段。它通过科学、客观、标准的测量方法对人的智力、一般能力倾向、特殊能力、性格特征、气质类型、职业兴趣和发展潜力等方面的素质进行分析和评价,为人才的选拔、录用、培养和配置以及个人的职业选择提供重要的参考。     

人工智能辅助下的心理健康新型测评

近年来, 人工智能技术的飞速发展及应用催生了“智能化心理健康测评”这一领域。智能化心理健康测评能够弥补传统方法的不足, 降低漏诊率并提高诊断效率, 这对于心理健康问题的普查及预警具有重大意义。目前, 智能化心理健康测评处于初步发展阶段, 研究者基于在线行为数据、便携式设备数据等开展主要以数据驱动为导向的探索研究, 旨在实现更高的预测准确率, 但是测评结果的可解释性等指标尚不够理想。未来的智能化心理健康测评需要强调心理学领域知识和经验的深度介入, 提高测评的针对性和精细化程度, 加强信效度检验, 这对于智能化心理健康测评工具的进一步发展和应用至关重要。     

无领导小组讨论的多侧面Rasch模型应用*

采用项目反应理论(IRT)的多侧面Rasch模型(MFRM),分析评价中心技术中无领导小组讨论(LGD)的测评结果,探讨被试能力水平、评委评分宽严度、评分内部一致性、维度难度和评定等级等问题,进而讨论各种偏差。通过 MFRM 分析人事测评结果,可深入了解被试能力的真实差异、甑别维度难度、探查测评误差源,从而完善测评试题编制、评估或诊断评委合格性、提高测评维度与测评目的匹配性,为拓展项目反应理论在人事测评中的应用提供独特视角。     

对文件筐测验(I-B)在选拔高层经理人员中的实证研究

以中国联通辽宁省分公司地市级副总经理选拔中收集到的数据,通过尝试采用文件筐测验的新型计分技术,分析研究了文件筐测验的信度和敛度。结果表明,新型计分技术可以有效改进传统计分技术的一些缺点,体现了文件筐测验未来的计分发展方向;新型计分技术基础上的评分一致性信度较高;在与由笔试、结构化面试和无领导小组讨论综合确定的选拔结果的比较中,文件筐测验获得了较高的同时效度。同时．研究也对文件筐测验结构效度方面存在的问题进行了分析,并对文件筐测验的进一步研究提出了建议。     

Incremental Validity of Leaderless Group Discussion Ratings Over and Above General Mental Ability and Personality in Predicting Promotion

Leaderless group discussions (LGDs) constitute one of the oldest assessment center exercises. In recent times, their added value has sometimes been questioned in light of trends to streamline assessment centers. The purpose of the present study is to examine the incremental validity of LGD ratings over cognitive ability scores and personality ratings for the prediction of extrinsic career success (i.e., promotion speed and number of promotions). We investigated this issue in the context of the promotion of French naval officers (N = 93) in an academy for high‐level executive positions over a 10‐year period. Results indicated that LGD ratings accounted for incremental variance in the prediction of promotion criterion measures, beyond cognitive ability and personality test scores. These results confirm that LGD ratings provide a unique contribution to the prediction of extrinsic career success in high‐level executive positions.     

Practical Intelligibility and Moral Skepticism: Should Realists Worry About Grass‐Counters and Hand‐Claspers?

The focus of this paper is the following claim: as a purely conceptual matter, the moral truths could be pretty much anything, and we should assume this in assessing our reliability at grasping moral truths. This claim, which I call No Content , plays a key role in an important skeptical argument against realist moral knowledge – the Normative Lottery Argument. In this paper, I argue that moral realists can, and should, reject No Content. My argument centers on the idea of practical intelligibility. I explore different aspects of practical intelligibility, and I argue that such intelligibility sets a constraint on the possibilities we should consider when assessing our reliability at grasping moral truths.     

7种嫉妒评估量表的信度与效度研究

研究西方7种嫉妒评估量表在中国使用的信度与效度。结果发现,7种嫉妒评估量表具有较高的分半信度和内部一致性信度;内容效度和效标关联效度能够满足中国被试者的使用要求;但各量表内容重复性较大,适用范围限于爱情及关系嫉妒,并不适合评估其他嫉妒类型。     

The role of individualism and the Five-Factor Model in the prediction of performance in a leaderless group discussion

Personality has seen a resurgence in the work performance literature. The Five-Factor Model (FFM) represents a set of personality factors that has received the most attention in recent years. Despite its popularity, the FFM may not be sufficiently comprehensive to account for relevant variation across performance dimensions or tasks. Accordingly, the present study also considers how individualism may predict additional variance in performance beyond the FFM. The study involved 152 undergraduate students who experienced a leaderless group discussion (LGD) exercise. Results showed that while the FFM accounted for variance in students' LGD performance, individualism (independence) accounted for additional, unique variance. Furthermore, analyses of the group compositions revealed curvilinear relationships between the relative amount of extraversion, conscientiousness, and individualism in relation to group-level performance.     

高中生数学元认知水平调查问卷的设计与编制*

对于元认知能力的评价和测试一直以来都是研究的难点,特别是就数学学科而言,已有研究多围绕数学问题解决过程中元认知监控水平的评价以及能力的培养展开,鲜有全面评价学生数学学习元认知水平的问卷。同时,没有针对高中生编制的元认知水平调查问卷。故本研究在已有研究的基础上,对已有的问卷进行修正和完善,通过征求专家意见与样本测试和数据分析,形成《高中生数学元认知水平调查问卷》。该问卷具有较好的内容效度和结构效度。信度方面,问卷整体的内部信度为0.952,分半信度为0.931,重测信度为0.946,说明问卷具有很好的内部一致性和测量稳定性。     

The Development and Evaluation of a Measure of Counselor Effectiveness

The purpose of this research was to construct and evaluate a measure for assessing counselor-trainee effectiveness. An eight-category rating instrument was constructed and two standardized interview situations emphasizing problems commonly encountered by secondary school counselors were developed. The standardized interview situations provided by the use of coached counselees permitted a panel of six trained judges to evaluate via closed-circuit television 30 counselor-trainees under conditions designed to insure comparability and, hence, fair appraisal. Using a definition of reliability as the degree of consistency between judges, the average correlation between ratings given by pairs of independent raters was .50. It was concluded that the rating instrument developed and the techniques employed for its use constituted a usable, realistic measure for assessing the counseling proficiency of counselor-trainees.     

Internal consistency reliability of the self-report antisocial process screening device

The self-report version of the Antisocial Process Screening Device (APSD) has become a popular measure for assessing psychopathic features in justice-involved adolescents. However, the internal consistency reliability of its component scales (Narcissism, Callous-Unemotional, and Impulsivity) has been questioned in several studies. This study evaluates the internal consistency reliability of the self-report APSD by examining various indices (e.g., Cronbach's alpha, mean interitem correlation) across 11 studies. Whereas the Narcissism and Impulsivity scales display moderate to good reliability, internal consistency indices for the Callous-Unemotional scale are consistently poor across studies. Suggestions are made for revisions to this scale that would substantially improve its internal consistency reliability.