A Comparison of Imputation Strategies for Ordinal Missing Data on Likert Scale Variables

This article compares a variety of imputation strategies for ordinal missing data on Likert scale variables (number of categories = 2, 3, 5, or 7) in recovering reliability coefficients, mean scale scores, and regression coefficients of predicting one scale score from another. The examined strategies include imputing using normal data models with naïve rounding/without rounding, using latent variable models, and using categorical data models such as discriminant analysis and binary logistic regression (for dichotomous data only), multinomial and proportional odds logistic regression (for polytomous data only). The result suggests that both the normal model approach without rounding and the latent variable model approach perform well for either dichotomous or polytomous data regardless of sample size, missing data proportion, and asymmetry of item distributions. The discriminant analysis approach also performs well for dichotomous data. Naïvely rounding normal imputations or using logistic regression models to impute ordinal data are not recommended as they can potentially lead to substantial bias in all or some of the parameters.     

Visual spatial constancy and modularity: Does intention penetrate vision?

Is vision informationally encapsulated from cognition or is it cognitively penetrated? I shall argue that intentions penetrate vision in the experience of visual spatial constancy: the world appears to be spatially stable despite our frequent eye movements. I explicate the nature of this experience and critically examine and extend current neurobiological accounts of spatial constancy, emphasizing the central role of motor signals in computing such constancy. I then provide a stringent condition for failure of informational encapsulation that emphasizes a computational condition for cognitive penetration: cognition must serve as an informational resource for visual computation. This requires proposals regarding semantic information transfer, a crucial issue in any model of informational encapsulation. I then argue that intention provides an informational resource for computation of visual spatial constancy. Hence, intention penetrates vision.     

The representation of category typicality in the frontal cortex and its cross-linguistic variations

When asked to judge the membership of typical (e.g., car) vs. atypical (e.g., train) pictures of a category (e.g., vehicle), native English (N = 18) and native Chinese speakers (N = 18) showed distinctive patterns of brain activity despite showing similar behavioral responses. Moreover, these differences were mainly due to the amount and pervasiveness of category information linguistically embedded in the everyday names of the items in the respective languages, with important differences across languages in how pervasive category labels are embedded in item-level terms. Nonetheless, the left inferior frontal gyrus and the bilateral medial frontal gyrus are the most consistent neural correlates of category typicality that persist across languages and linguistic cues. These data together suggest that both cross- and within-language differences in the explicitness of category information have strong effects on the nature of categorization processes performed by the brain.     

Non-selective lexical access in bilinguals is spontaneous and independent of input monitoring: Evidence from eye tracking

Language non-selective lexical access in bilinguals has been established mainly using tasks requiring explicit language processing. Here, we show that bilinguals activate native language translations even when words presented in their second language are incidentally processed in a nonverbal, visual search task. Chinese–English bilinguals searched for strings of circles or squares presented together with three English words (i.e., distracters) within a 4-item grid. In the experimental trials, all four locations were occupied by English words, including a critical word that phonologically overlapped with the Chinese word for circle or square when translated into Chinese. The eye-tracking results show that, in the experimental trials, bilinguals looked more frequently and longer at critical than control words, a pattern that was absent in English monolingual controls. We conclude that incidental word processing activates lexical representations of both languages of bilinguals, even when the task does not require explicit language processing.     

家庭因素中父母情感温暖、文化性与责任心对大学生职业决策自我效能的中介与中介调节研究

目的：探讨大学生家庭因素中父母情感温暖教养方式、文化性家庭环境与责任心对职业决策自我效能的中介效应与中介调节效应。方法：采用责任心量表、职业决策自我效能量表、父母教养方式评价量表和家庭环境量表,对大学四个年级1207名学生进行测量,运用SPSS12.0、AMOS17.0对数据进行统计分析。结果：（1）父母情感温暖通过责任心对大学生职业决策自我效能具有稳定而持久的间接作用。（2）文化性作为父母情感温暖的调节变量,其与父母情感温暖的交互作用对责任心具有明显的预测作用,并通过责任心中介变量,对大学生职业决策自我效能产生稳定而持久的间接作用。     

题目因素分析：基于SEM和基于IRT的两类方法

心理和教育测量一般只能达到顺序量表的水平,其测量数据与被测因子间并非简单线性关系。题目因素分析是用来描述测量题目与因子间非线性关系的统计模型。题目因素分析主要有基于结构方程模型和基于项目反应理论两类方法,两类方法之间存在紧密的联系,甚至可以看作是同一模型的两种表现形式。本文详细阐述了该关系,同时对两类方法在参数估计、模型拟合指标、测量一致性检验和支撑软件等方面的特点进行了分析和比较,以便研究者选择最为适合其研究的方法。     

心理健康素质测评系统·中国成年人应对风格量表的编制

编制适用于我国成年人使用的应对风格量表。通过对应对风格研究的文献分析,将应对风格量表确定为注重问题的应对策略和注重情绪的应对策略两个维度,编写项目43个,通过对410和379人的大学生样本的两次预测分析,形成由33个项目的正式量表。通过对467人的成年人样本和来自大学生的三组样本的实测,考察量表的各项心理测量学指标。结果表明,应对风格量表具有较好的内部一致性信度和重测信度,也具有较好的结构效度、内容效度、聚合效度和效标效度。中国成年人应对风格量表具有可靠的心理测量学特征,可以被用于中国成年人应对风格的评估     

大学生人际信任半径与信任水平研究

自编《大学生内-外信任问卷》,考察大学生人际信任半径和信任水平的现状,结果表明:(1)问卷具有良好的信度和效度;(2)男生的信任半径大于女生,信任水平低于女生;(3)学生干部的信任半径小于非学生干部,信任水平高于非学生干部;(4)大学生信任半径随着消费水平的升高而减小;(5)高年级学生的信任半径大于低年级学生,信任水平却低于低年级学生;(6)信任半径和信任水平呈现出相反的变化趋势。     

认知闭合需要与启发式策略对价格判断的影响

采用问卷与实验相结合的方法,以120名大学生为被试,考察认知闭合需要与一般启发式策略对个体价格判断的潜在影响。结果发现:(1)认知闭合需要与精确度效应交互作用显著,高闭合个体在整数价格高低的评价上高于低闭合个体;(2)认知闭合需要与差价大小交互作用显著,差价整数位是3时高闭合个体对于差价的评价高于低闭合者;(3)认知闭合需要,左侧数字改变与以9结尾、以0结尾三者的交互作用显著,当评价左侧数字改变的价格时,高闭合个体对以0结尾的数字的评价显著高于以9结尾的数字的评价。认知闭合需要与启发式策略对价格判断共同产生影响。研究结果表明,不同的定价方式与定价策略会对认知闭合需要不同的个体产生差异性影响。