A cautionary note on the use of probability values to evaluate interobserver agreement

Proposed methods of assessing the statistical significance of interobserver agreements provide erroneous probability values when conducted on serially correlated data. Investigators who wish to evaluate interobserver agreements by means of statistical significance can do so by limiting the analysis to every k(th) interval of data, or by using Markovian techniques which accommodate serial correlations.     

Weighted minimum trace factor analysis

In the last decade several authors discussed the so-called minimum trace factor analysis (MTFA), which provides the greatest lower bound (g.l.b.) to reliability. However, the MTFA fails to be scale free. In this paper we propose to solve the scale problem by maximization of the g.l.b. as the function of weights. Closely related to the primal problem of the g.l.b. maximization is the dual problem. We investigate the primal and dual problems utilizing convex analysis techniques. The asymptotic distribution of the maximal g.l.b. is obtained provided the population covariance matrix satisfies sone uniqueness and regularity assumptions. Finally we outline computational algorithms and consider numerical examples.I wish to express my gratitude to Dr. A. Melkman for the idea of theorem 3.3.     

The comparative effectiveness of two modes of observer training on the Staff-Resident Interaction Chronograph

The comparative effectiveness of two time-limited modes of training observers to code activity on the Staff-Resident Interaction Chronograph (SRIC) in residential treatment programs for mentally disabled adults was evaluated. The susceptibility of training procedures for consensual observer drift was also examined, as was the predictability of SRIC mastery from trainee characteristics. Two equated groups of undergraduate student trainees (N=15 each) participated in full-time training for 27 days, followed by two weeks of criterion testing in vivo and on videotapes. One group received training by experience personnel using procedures known to be effective (original method). The other group received training via a previously untested set of written and videotaped procedures that do not rely on experienced personnel (package method). Multivariate and univariate analyses of variance found both methods to be equally effective in the degree of mastery achieved by trainees, without evidence of observer drift. No meaningful predictions of coding mastery were found, but conceptual mastery was predictable from individual characteristics. Differences were obtained for both groups between in vivo versus videotaped criterion tests. The results document procedures that are both efficient and resistant to invalidity for complex observational methodology as well as feasible for standardizing assessment of staff functioning across residential settings.This article is based on a thesis submitted to the Graduate College of the University of Illinois at Urbana-Champaign in partial fulfillment of the requirements for the Ph.D. degree in psychology by the first author under direction of the second author. The third and fourth authors also participated as supervisors. Appreciation is extended to other members of the thesis committee, Fred Kanfer, W. Robert Nay, Julian Rappaport, and James Wardrop, for their comments and recommendations. This study was partially supported by Public Health Service Grants MH-25464 and MH-14257 from the National Institute of Mental Health, and by grants from The Joyce Foundation and the Illinois Department of Mental Health and Developmental Disabilities.     

An investigation of children's fears and their mothers' fears

Children (75 female, 52 male) in grades 2 through 8 completed the Fear Survey Schedule for Children (FSS-FC). Their mothers completed the same questionnaire twice: once for themselves and a second time to estimate their children's fears. Spearman's rhos indicated that there was a high degree of correspondence between the mothers' rank-ordered estimates of their children's fears and the children's rank-ordered self-reports (=.86 for males, =.96 for females.However, mothers' overall estimates of their children's general fearfulness were significantly correlated only with their daughters' fearfulness, not with their sons'. Further analyses showed that mothers could generally identify their children's highest-rated fears. All test-retest measures were significant. In summary, these results suggest that mothers may provide useful clinical information about their children's specific fears and that the FSS-FC is a reliable instrument with which to assess children's fears.     

运动情境四维成就目标定向量表的初步编制——以第十二届特奥会中国籍智力残疾运动员为被试

该研究在文献分析和访谈的基础上,确定智力残疾运动领域成就目标定向的四维结构并编制初测问卷。对400名特奥会运动员进行了施测,对数据进行项目分析、验证性因素分析和信度分析。验证性因素分析和信度分析显示,问卷具有较好的效度和信度,可以作为运动领域四维目标定向的测量工具。     

非词复述测验的编制和初步分析

本研究编制了一种用于测量儿童语音工作记忆的测验———非词复述测验,并在48名四年级小学生中初步进行信度、效度检验和项目分析。结果表明:(1)该测验有较高的重测信度;(2)该测验具有较高的结构效度和效标效度;(3)分测验二的项目难度分布比较合理,多数项目鉴别力较高,而分测验一的项目难度分布和项目鉴别力则有待于在今后的研究中进一步提高。     

变革型领导风格的实证研究

以72家企业的193名管理者为被试,通过多来源评估法收集数据,采用因素分析、信度分析和回归分析等方法对变革型领导的理论结构及其与领导有效性的关系进行了深入研究。结果表明,变革型领导具有二阶单因素结构。即四个独立子因素为领导魅力、感召力、智力激发和个性化关怀,这些子因素归属于一个单一二阶因素;研究所使用的《变革型领导问卷》具有良好的构想效度和信度,适用于中国文化;变革型领导及其子维度对领导有效性有一定的预测力。     

大学生地域歧视现象态度量表的编制及信效度检验

地域歧视现象的存在是违背和谐社会理念的,人们对此现象是什么态度?研究以费施贝因和阿扎吉提出的理性行为模型理论为基础,选取网络上最活跃的大学生为样本,编制了大学生地域歧视现象态度量表,构建了对地域歧视现象态度、对地域歧视者态度和对被歧视者态度3个维度。通过整理访谈资料、参考相关量表、专家讨论等方法编制条目。选取358名被试进行预测试,617名被试正式测试。研究结果表明,大学生地域歧视现象态度量表建构的3个维度结构合理,量表的项目分析、探索性分析和验证性分析符合心理测量学要求,是测量中国大学生地域歧视现象态度的有效工具。     

真实自豪与自大自豪倾向量表的修订及适用

对Tracy和Robins编制的真实自豪与自大自豪倾向量表进行中文版修订并初步考察我国大学生自豪感的特点,分别选取202名和484名大学生进行问卷预测和正式施测。验证性因素分析表明修订后量表仍保持英文版的双维结构,两分量表的α系数为0.785和0.743,重测信度为0.978和0.952。修订后量表具有良好的心理测量学指标,可以用于我国大学生的测试。进一步发现我国大学生的真实自豪显著高于自大自豪,大学生自豪感不存在性别差异,自大自豪存在显著的年级差异。