A Signal Detection Model for Multiple-Choice Exams

A model for multiple-choice exams is developed from a signal-detection perspective. A correct alternative in a multiple-choice exam can be viewed as being a signal embedded in noise (incorrect alternatives). Examinees are assumed to have perceptions of the plausibility of each alternative, and the decision process is to choose the most plausible alternative. It is also assumed that each examinee either knows or does not know each item. These assumptions together lead to a signal detection choice model for multiple-choice exams. The model can be viewed, statistically, as a mixture extension, with random mixing, of the traditional choice model, or similarly, as a grade-of-membership extension. A version of the model with extreme value distributions is developed, in which case the model simplifies to a mixture multinomial logit model with random mixing. The approach is shown to offer measures of item discrimination and difficulty, along with information about the relative plausibility of each of the alternatives. The model, parameters, and measures derived from the parameters are compared to those obtained with several commonly used item response theory models. An application of the model to an educational data set is presented.     

Response bias,recollection, and familiarity in individuals with Highly Superior Autobiographical Memory (HSAM)

ABSTRACT

The current study focused on individuals with Highly Superior Autobiographical Memory (HSAM) and had two main objectives: 1) investigate whether HSAMs have increased recollection performance compared to controls, and 2) investigate whether HSAMs have a reliably different response bias than controls. While previous lab-based recognition tests have shown that HSAMs have normal memory performance, these tests were based on a mixture of both recollection and familiarity. Here, we employed recognition tests specifically designed to separate recollected responses from those based on familiarity. Additionally, we were interested in how HSAMs make their memory decisions. Several studies have shown a great deal of variability between individuals in their response bias. Here, individuals with HSAM and age- matched controls completed a remember/know and a source memory test. HSAMs behaved like controls in both overall and recollection-based memory discrimination. However, HSAMs showed a significantly more liberal response bias, endorsing more items as “old” than controls. These findings contribute to our understanding of how memory processes – especially those related to decision-making – function in those with superior memory abilities and may help elucidate how other (non-HSAM) memory experts make decisions.     

Retrieval of names in face and object naming in an interference study

Two experiments using the interference paradigm are reported. In the first experiment, the participants spoke aloud the names of celebrities and the names of objects when presented with pictures while hearing distractors. In the case of proper names, we replicated the data obtained by Izaute and Bonin (2001) using the interference paradigm with a proper name written naming task. In the case of common names, the results replicated those obtained by Shriefers, Meyer, and Levelt (1990). In the second experiment, the participants produced the names of celebrities when presented with their faces while hearing distractors that were either proper names associated with the celebrities (associate condition), that belonged to a different professional category (different condition), or that corresponded to the proper names of the celebrities (identical condition). For negative SOAs, “associate” distractors were found to increase latencies compared to the “different category” condition. The implications of the findings for proper name retrieval are briefly discussed.     

认知心理学视角下的医师告知义务探析

Ellis的ABC理论和Schachter的情绪认知理论及试验说明,个体的认知信念影响情绪和行为反应.也就是说,患者对疾病事件的认知评价直接影响着情绪和行为表现.因此,在认知心理学相关理论指导下,医师对患者履行告知义务时必须遵循准确性原则、个性化原则及艺术性原则等,让患者对疾病事件有充分的知情与信息掌握,帮助患者改变观察问题的角度,正确认知与评价疾病事件,进而以积极、健康的情绪和行为表现来配合医务人员的诊治.     

认知诊断分类中心的确定

期望反应模式是认知诊断分类的类中心,确定了诊断范围中属性及其层级关系后,类中心的数目由测验Q矩阵决定.类中心应该是完备的,即理论上有多少个知识状态就应该有多少个类中心,这涉及评分方式、Q矩阵设计、Q矩阵评价与修改、认知诊断测验如何实施等问题的讨论.重点给出多级评分认知诊断测验不同属性层级对应的完备Q矩阵设计的例子和罗列了Wang等人（2013）的Q矩阵修改的方法.     

项目反应理论原理与当前应用热点概览

本文首先分析了经典测验理论存在的局限,然后在潜在特质理论和项目特征曲线两大概念基础上阐述了项目反应理论及其基础模型的测量学原理,介绍了多个项目反应理论基础模型.最后简要介绍了七项当前应用项目反应理论指导大型题库建设和指导编制各种新型测验的热点内容.     

Bases of social power,leadership styles,and organizational commitment

Affective organizational commitment reflects the extent to which organizational members are loyal and willing to work toward organizational objectives (Meyer & Allen, 1997). In particular, affective organizational commitment holds very important implications at all organizational levels (e.g., turnover rates, performance, and citizenship behavior). Whereas previous research has evinced the positive influence of transformational and charismatic leadership styles on affective commitment toward the organization (Bass & Avolio, 1994), little is known with regard to the nature of this relationship. In line with the interpersonal power/interaction model, the present investigation aimed to investigate the mechanism at play between transformational leadership style and affective organizational commitment. Specifically, we hypothesized that transformational leadership style would increase affective organizational commitment through its effect on willingness to comply with soft bases of power. In two studies, we subjected the foregoing hypotheses to empirical scrutiny. In Study 1, the proposed mediation model was empirically supported with Italian employees in the public sector. Attesting to the robustness of our findings, Study 2 replicated the findings of Study 1 with Italian employees from the public and private sectors. In addition, Study 2 replicated Study 1 using a different measure of transformational leadership. Both Study 1 and Study 2 provided results consistent with our hypotheses. Specifically, the present paper reports empirical evidence that (1) the more participants report having a transformational leader, the more willing they become to comply with soft (but not harsh) power bases, (2) in turn, greater willingness to comply with soft (but not harsh) power bases increases one's affective organizational commitment. These findings provide additional support for the interpersonal power/interaction model and pave the way for new research directions.     

The Influence of Attitude on Learning

Automaticity theory and the effect of coloring a single element were tested with all or only 1 element colored in Stroop tasks. The 312 participants in 5 experiments indicated stimulus presentation color by key press. Experiments 1 and 2 replicated those of D. Besner, J. A. Stoltz, and C. Boutilier (1997) with some changes, and revealed similar results: less Stroop interference with only 1 letter colored. Besner et al. (1997) interpreted the results as indicating that coloring a single letter eliminates automatic reading processes. The cause of that reduction in Stroop interference was investigated in Experiments 3, 4, and 5 using color words, bars, and rectangles. The effect of coloring 1 element was to increase color-naming time by the same amount for congruent and neutral, nonverbal stimuli, but not for incongruent stimuli. The results are interpreted in terms of automaticity theory, and a continuous flow approach to the Stroop effect is presented.     

Latent variables should remain as such: Evidence from a Monte Carlo study

Use of subject scores as manifest variables to assess the relationship between latent variables produces attenuated estimates. This has been demonstrated for raw scores from classical test theory (CTT) and factor scores derived from factor analysis. Conclusions on scores have not been sufficiently extended to item response theory (IRT) theta estimates, which are still recommended for estimation of relationships between latent variables. This is because IRT estimates appear to have preferable properties compared to CTT, while structural equation modeling (SEM) is often advised as an alternative to scores for estimation of the relationship between latent variables. The present research evaluates the consequences of using subject scores as manifest variables in regression models to test the relationship between latent variables. Raw scores and three methods for obtaining theta estimates were used and compared to latent variable SEM modeling. A Monte Carlo study was designed by manipulating sample size, number of items, type of test, and magnitude of the correlation between latent variables. Results show that, despite the advantage of IRT models in other areas, estimates of the relationship between latent variables are always more accurate when SEM models are used. Recommendations are offered for applied researchers.     

Sequential Aiming with Two Limbs and the One-Target Advantage

Movement times to the first target in a 2-target sequence are typically slower than in 1-target aiming tasks. The 1-target movement time advantage has been shown to emerge regardless of hand preference, the hand used, the amount of practice, and the availability of visual feedback. The authors tested central and peripheral explanations of the 1-target advantage, as postulated by the movement integration hypothesis, by asking participants to perform single-target movements, 2-target movements with 1 limb, and 2-target movements in which they switched limbs at the first target. Reaction time and movement time data showed a 1-target advantage that was similar for both 1- and 2-limb sequential aiming movements. This outcome demonstrates that the processes underlying the increase in movement time to the 1st target in 2-target sequences are not specific to the limb, suggesting that the 1-target advantage originates at a central rather than a peripheral level.