The greatest lower bound to the reliability of a test and the hypothesis of unidimensionality

To assess the reliability of congeneric tests, specifically designed reliability measures have been proposed. This paper emphasizes that such measures rely on a unidimensionality hypothesis, which can neither be confirmed nor rejected when there are only three test parts, and will invariably be rejected when there are more than three test parts. Jackson and Agunwamba's (1977) greatest lower bound to reliability is proposed instead. Although this bound has a reputation for overestimating the population value when the sample size is small, this is no reason to prefer the unidimensionality-based reliability. Firstly, the sampling bias problem of the glb does not play a role when the number of test parts is small, as is often the case with congeneric measures. Secondly, glb and unidimensionality based reliability are often equal when there are three test parts, and when there are more test parts, their numerical values are still very similar. To the extent that the bias problem of the greatest lower bound does play a role, unidimensionality-based reliability is equally affected. Although unidimensionality and reliability are often thought of as unrelated, this paper shows that, from at least two perspectives, they act as antagonistic concepts. A measure, based on the same framework that led to the greatest lower bound, is discussed for assessing how close is a set of variables to unidimensionality. It is the percentage of common variance that can be explained by a single factor. An empirical example is given to demonstrate the main points of the paper. The authors are obliged to Henk Kiers for commenting on a previous version. Gregor Sočan is now at the University of Ljubljana.     

Reliability as a function of the number of item options derived from the “knowledge or random guessing” model

For (0, 1) scored multiple-choice tests, a formula giving test reliability as a function of the number of item options is derived, assuming the knowledge or random guessing model, the parallelism of the new and old tests (apart from the guessing probability), and the assumptions of classical test theory. It is shown that the formula is a more general case of an equation by Lord, and reduces to Lord's equation if the items are effectively parallel. Further, the formula is shown to be closely related to another formula derived from Lord's randomly parallel tests model.     

不同类型考试焦虑影响考试成绩的差异模式

调查了440名高中生,以不同类型考试焦虑为预测变量,以掌握目标、情绪性、应对反应、考试自我效能感、成绩-接近目标、成绩-回避目标、担忧、学习和考试技能、认知干扰为中介变量,期末数学考试成绩为最终结果变量,探讨不同类型考试焦虑影响考试成绩的模式。结果表明:不同类型考试焦虑具有不同的影响考试成绩的模式,即存在认知主导型模式(简称C模式)、生理唤醒主导型模式(简称P模式)、技能缺乏主导型模式(S模式)等三种不同的模式。担忧是C模式中的主要中介变量,P模式的主要特征是担忧对情绪性存在显著影响,S模式的特点是中介变量较少,学习和考试技能变量受考试焦虑和考试自我效能感双重影响并作用于考试成绩。     

物理概念图试题的评分方法

详细介绍了运用知识编码对物理概念图试题进行评分的具体方法,并对物理概念图试题的难度、区分度、信度和效度进行了检验,计算了物理概念图试题与传统物理题型共同组成的期末物理测验的信度,说明依据知识编码评定物理概念图试题分数,是一种行之有效的评分方法,按照知识编码评定物理概念图试题的分数使物理概念图试题成为一道高质量的试题。     

智力测验分数解释的发展趋势

智力测验分数的解释是智力心理学一个重要的研究领域。智力测验分数解释最基本的一个目的就是为了理解。随着智力理论和智力测验的发展,智力测验分数的解释出现了一些新的特点与趋势即注重智力测验分数解释的理论基础,注重智力测验分数解释的效度丰富化与从有用信息的抽取来解释测验分数的趋向。     

A Swedish non-word repetition test for preschool children

A Swedish non-word repetition test for preschool children was constructed with the aim of measuring short-term phonological memory, which has been shown to correlate with language development and language proficiency. Normative data based on results for 200 children four to six years of age are presented. An item analysis of the original 30-item test resulted in a shortened 24 non-word version found suitable for four- to six-year old children. Results for this shortened version, which had a Cronbach's alpha of 0.73, showed longer non-words to be more difficult to repeat than shorter ones, and significant effects of age and compatibility of the tester's and the child's accent, but not of gender. The results are discussed within the framework of Baddeley's working memory model.     

The Early Numeracy Test in Finnish: children's norms

This article concerns psychometric aspects of the Finnish Early Numeracy Test, which has been translated from the original Dutch Early Numeracy Test. The advantage of the test is that young children's numerical skills can be assessed systematically, which was not possible previously in Finland. A norm study was conducted in which the test was administered to a representative sample of 1,029 Finnish children. The reliability and validity results justify the use of the test as an early-childhood screening test and in research on number sense. The indicative effects of gender, parental professional education, domicile and number of siblings are discussed.     

学习焦虑、学习态度和投入动机与学业成绩关系的研究——关于《心理统计学》学习经验的调查

本研究对122名本科生《心理统计学》课程的学习经验进行调查,其结果为:(1)在该课程的学习经验和考试成绩上男、女生差异显著,它表现在学习态度层面的有用性和成就态度,投入动机层面的自我投入上女生均优于男生;研究还发现,考分低则焦虑水平较高;(2)学习焦虑、学习态度、投入动机与考试成绩之间有显著相关,其中学习焦虑与成绩呈负相关,学习态度、投入动机与成绩呈正相关;(3)学习焦虑,学习态度和投入动机均影响学习成绩。学习成绩不仅受到学习焦虑和投入动机的直接影响,还受到学习态度等因素的间接影响。     

A new method of administering the Grooved Pegboard Test: performance as a function of handedness and sex

The purpose of the present study was twofold: first to examine the influences of sex and handedness on manual performance on the Grooved Pegboard Test; and secondly to provide normative data for two versions (Place and Remove tasks) of the Grooved Pegboard Test, as previous work (Bryden & Roy, 1999) had suggested that the Remove task of the Grooved pegboard may provide a purer measure of motor speed of the two hands than the standard administration of the Grooved Pegboard Test. One hundred and fifty-three (47 males and 106 females) participants completed the Grooved Pegboard Test. Individuals performed the standard version of the Grooved Pegboard Test (Place task) and a novel version of the test (Remove task). In the standard version, participants were timed on their speed for placing the pegs, while in the novel version they were timed on their speed for removing the pegs. Results confirmed previously noted hand and sex differences in the Place task of the Grooved Pegboard Test, as well as the lack of effect of handedness on performance (Bornstein, 1995; Ruff & Parker, 1993). Significant performance differences between the hands were also noted for the Remove task. Findings also indicated that the Remove task was sensitive to sex and handedness effects.     

Time ordering in frontal lobe patients: a stochastic model approach

Frontal lobe patients reproduced a sequence of capital letters or abstract shapes. Immediate and delayed reproduction trials allowed the analysis of short- and long-term memory for time order by means of suitable Markov chain stochastic models. Patients were as proficient as healthy subjects on the immediate reproduction trial, thus showing spared encoding and short-term memory. They failed, instead, on the delayed trials with capital letters, but not with random shapes, suggesting that their long-term memory impairment did not depend on primary deficits for ordering, but on inability to benefit from the organisational strategies that improve the retention and retrieval in normal subjects.