Analysis of Interactions and Nonlinear Effects with Missing Data: A Factored Regression Modeling Approach Using Maximum Likelihood Estimation

Abstract

When estimating multiple regression models with incomplete predictor variables, it is necessary to specify a joint distribution for the predictor variables. A convenient assumption is that this distribution is a multivariate normal distribution, which is also the default in many statistical software packages. This distribution will in general be misspecified if predictors with missing data have nonlinear effects (e.g., x²) or are included in interaction terms (e.g., x·z). In the present article, we introduce a factored regression modeling approach for estimating regression models with missing data that is based on maximum likelihood estimation. In this approach, the model likelihood is factorized into a part that is due to the model of interest and a part that is due to the model for the incomplete predictors. In three simulation studies, we showed that the factored regression modeling approach produced valid estimates of interaction and nonlinear effects in regression models with missing values on categorical or continuous predictor variables under a broad range of conditions. We developed the R package mdmb, which facilitates a user-friendly application of the factored regression modeling approach, and present a real-data example that illustrates the flexibility of the software.     

Research about the university teaching performance evaluation under the data envelopment method

How to take active and effective measures to evaluate the university scientifically and rationally has been an eternal topic that the educational circles are constantly exploring. Based on the principle of index construction, the current educational performance evaluation index system is improved and a more reasonable evaluation index system is formed. On this basis, taking the sample data in 2017 as an example, the principal component analysis method is used to reduce the dimension of input and output indicators and eliminate the correlation between indicators, and three principal components of input and three principal components of output are obtained. Secondly, data envelopment analysis model is established, and the data processed are analyzed with the help of MATLAB and DEAP2.1 operation software. The efficiency of these 24 colleges and universities is compared to understand the efficiency and differences of each college. Moreover, projection analysis of non-DEA effective DMU is completed and the direction of improvement and the specific adjustment value are pointed out.     

Exploration of anomalous perceptual experiences in migraine between attacks using the Cardiff Anomalous Perceptions Scale

Distortions in sensory experiences that precede a migraine attack have been extensively documented, the most well-known being the visual aura. Distortions in the experience of other senses are also reported as part of an aura, albeit less frequently, together with changes in the perception or ownership of the body or body parts. There are many examples of differences in aspects of visual perception between migraine and control groups, between attacks, but not as much on unusual experiences involving other senses, the sense of the body or the experience of the environment. Seventy-seven migraine (33 with aura) and 74 control participants took part. Anomalous perceptions were experienced by both migraine and control groups, but more with migraine experienced them and rated them as more distressing, intrusive and frequent. Associations with reports of visual triggers of migraine and visual discomfort are presented. This study is the first to show relationships between these factors.     

Predicting physical activity intention and behaviour using achievement goal theory: A person-centred analysis

The purpose of the current study was to identify the 2 × 2 achievement goals profiles at the intraindividual level using a latent profile analyses (LPA) approach while controlling for the nesting of students within classroom. Additional analyses involving the direct inclusion of predictors and outcomes to the final latent profile solution were also used to examine the relationships between the latent profiles and perceived motivational climate, intention to be physically active and physical activity participation. A sample of 1810 school children aged 14–19 years drawn from 79 classes in 13 Singaporean schools took part in the study. Using the latent profile analysis, four distinct motivational profiles could be identified. The results from multinomial logistic regressions showed that profile membership was significantly predicted by perceptions of mastery and performance climate. Finally, the results showed that the four profiles differed significantly in terms of intention to be physically active and physical activity participation.     

道德的轻与重：道德的重量具身效应及隐喻的调节作用

本研究采用行为反应时和事件相关电位(ERP)探讨道德的重量具身效应及“重量-道德”隐喻联结对该效应的调节作用。参考内隐联想测验的逻辑，采用联合分类反应任务，在默认的“重量-道德”隐喻表征情境（实验1）和道德垂直空间隐喻的启动情境（实验2）中，要求被试分别使用轻鼠标和重鼠标对道德/不道德词进行分类判断，考察鼠标重量对道德概念的加工所产生的影响。结果显示，在默认情境中，“重-道德，轻-不道德”的联合分类条件比“轻-道德，重-不道德”条件的分类反应时更短，并伴随有更大的脑电晚期正成分（LPC），而在启动道德垂直空间隐喻后，两种联合分类条件下的反应时和LPC结果出现反转。本研究结果表明道德概念的加工会受到重量经验的影响，“重量-道德”具身效应具有心理现实性，且重量概念与道德概念的隐喻联结引导并调节了这种具身效应。