A model-based approach to multivariate principal component regression: Selecting principal components and estimating standard errors for unstandardized regression coefficients

Principal component regression (PCR) is a popular technique in data analysis and machine learning. However, the technique has two limitations. First, the principal components (PCs) with the largest variances may not be relevant to the outcome variables. Second, the lack of standard error estimates for the unstandardized regression coefficients makes it hard to interpret the results. To address these two limitations, we propose a model-based approach that includes two mean and covariance structure models defined for multivariate PCR. By estimating the defined models, we can obtain inferential information that will allow us to test the explanatory power of individual PCs and compute the standard error estimates for the unstandardized regression coefficients. A real example is used to illustrate our approach, and simulation studies under normality and nonnormality conditions are presented to validate the standard error estimates for the unstandardized regression coefficients. Finally, future research topics are discussed.     

Broad or narrow affect scores for the Multiple Affect Adjective Check List? Comment on Hunsley's “dimensionality of the Multiple Affect Adjective Check List-Revised”

Hunsley's paper constitutes the second independent replication of four of the five factors in the Multiple Affect Adjective Check List-Revised (MAACL-R), even though he used the trait instead of the state form used to construct the scales and a more stringent factor loading criterion than Zuckerman and Lubin. Hunsley also did a two-factor analysis (positive and negative affects) of the MAACL items and concluded on the basis of the scree test that this was a more optimal solution than the five-factor one. This conclusion is questioned on the basis that the scales were devised to improve discriminant validity of the subscales, which they have done, particularly if standard scores are used. Since four of the five factors are replicable in state and trait versions of the MAACL-R and clinical studies show discriminant validity for the subscales, there is no reason to ignore the components of the two broader affect factors. Such factors can be assessed through use of the two standard summary scores for the MAACL: Dysphoria (A + D + H) and Positive Affect plus Sensation Seeking (PA + SS).     

A simulated annealing methodology for clusterwise linear regression

In many regression applications, users are often faced with difficulties due to nonlinear relationships, heterogeneous subjects, or time series which are best represented by splines. In such applications, two or more regression functions are often necessary to best summarize the underlying structure of the data. Unfortunately, in most cases, it is not known a priori which subset of observations should be approximated with which specific regression function. This paper presents a methodology which simultaneously clusters observations into a preset number of groups and estimates the corresponding regression functions' coefficients, all to optimize a common objective function. We describe the problem and discuss related procedures. A new simulated annealing-based methodology is described as well as program options to accommodate overlapping or nonoverlapping clustering, replications per subject, univariate or multivariate dependent variables, and constraints imposed on cluster membership. Extensive Monte Carlo analyses are reported which investigate the overall performance of the methodology. A consumer psychology application is provided concerning a conjoint analysis investigation of consumer satisfaction determinants. Finally, other applications and extensions of the methodology are discussed.     

The Italian Red Brigades and the structure and dynamics of terrorist groups

One of the problems in dealing with terrorism is that we have virtually no access to individual terrorists; only their actions are visible. The founders of the Italian terrorist group, the Red Brigades, on the other hand, have written about their experiences and have exhaustively explained their motivations. The author’s premise is that these autobiographies and her interviews with several of the group’s members give us access to the unconscious processes involved in the formation and operation of the group. After terrorist attacks, it is natural to ask whether the terrorists’ capacity for collective violence is an indication of personal pathology. This paper argues that the relevant pathology in the terrorist enterprise is not that of the individual but that of the group. Relying on the theories of groups of Freud (1921), Bion (1961), Anzieu (1984) and Kaes (2007), the author argues that psychoanalytic theory is essential to understanding the motivations and actions of violent groups which otherwise remain obscure. Although the discussion has been confined to one terrorist group, the author hopes that it can also be useful for understanding the unconscious dynamics of other groups structured around an ideology which mandates the destruction of human life.     

Regression and new beginnings: Michael, Alice and Enid Balint and the circulation of ideas

This article offers a new evaluation of Michael Balint's history. It starts with his growing up in Hungary and examines the central concepts of his writing: the analytic pair, regression and the basic fault and creativity, up to and including his renowned work on the eponymous Balint groups (which forged a unique link between psychoanalysis and medicine). While his name is, of course, well known, this article aims to bring his ideas to the attention of a modern analytic audience. Having trained in the 1920s with Ferenczi, Balint brought Ferenczi's literary inheritance to England where he lived until his death in 1970. His connections to Klein, Winnicott and Lacan, all of whom respected his analytic stance, are also examined. Furthermore, this article argues that his ideas were filtered through the theoretical lens of his first wife Alice Balint and later through Enid Balint, both of whom played a key - and rarely recognised - role in the development of his thought. It ends with a brief discussion of his ideas on analytic training and his quest, successful only after his death, to publish the complete Freud-Ferenczi correspondence, together with Ferenczi's diary.     

What Causes the Mean Bias of the Likelihood Ratio Statistic with Many Variables?

Abstract

Survey data often contain many variables. Structural equation modeling (SEM) is commonly used in analyzing such data. However, conventional SEM methods are not crafted to handle data with a large number of variables (p). A large p can cause T_ml, the most widely used likelihood ratio statistic, to depart drastically from the assumed chi-square distribution even with normally distributed data and a relatively large sample size N. A key element affecting this behavior of T_ml is its mean bias. The focus of this article is to determine the cause of the bias. To this end, empirical means of T_ml via Monte Carlo simulation are used to obtain the empirical bias. The most effective predictors of the mean bias are subsequently identified and their predictive utility examined. The results are further used to predict type I errors of T_ml. The article also illustrates how to use the obtained results to determine the required sample size for T_ml to behave reasonably well. A real data example is presented to show the effect of the mean bias on model inference as well as how to correct the bias in practice.     

Project DyAdd: Visual attention in adult dyslexia and ADHD

In this study of the project DyAdd, three aspects of visual attention were investigated in adults (18–55 years) with dyslexia (n = 35) or attention deficit/hyperactivity disorder (ADHD, n = 22), and in healthy controls (n = 35). Temporal characteristics of visual attention were assessed with Attentional Blink (AB), capacity of visual attention with Multiple Object Tracking (MOT), and spatial aspects of visual attention with Useful Field of View (UFOV) task. Results showed that adults with dyslexia had difficulties performing the AB and UFOV tasks, which were explained by an impaired ability to process dual targets, longer AB recovery time, and deficits in processing rapidly changing visual displays. The ADHD group did not have difficulties in any of the tasks. Further, performance in the visual attention tasks predicted variation in measures of phonological processing and reading when all of the participants were considered together. Thus, difficulties in tasks of visual attention were related to dyslexia and variation of visual attention had a role in the reading ability of the general population.     

How distraction affects pedestrian response: Evidence from behavior patterns and cortex oxyhemoglobin changes

ObjectivesDistracted walking is a major cause of pedestrian road traffic injuries, but little is known about how distraction affects pedestrian safety. The study was designed to explore how visual and auditory distraction might influence pedestrian safety.MethodsThree experiments were conducted to explore causal mechanisms from two theoretical perspectives, increased cognitive load from the distraction task and resource competition in the same sensory modality. Pedestrians’ behavior patterns and cortex oxyhemoglobin changes were recorded while they performed a series of dual tasks.ResultsFour primary results emerged: (a) participants responded more slowly to both visual and auditory stimuli in traffic, as well as walked more slowly, while talking on the phone or text messaging compared to when undistracted or listening to music; (b) when participants completed pedestrian response tasks while distracted with a high cognitive load, their response was significantly slower and poorer than when they carried out a lower cognitive load distraction task, (c) participants had higher levels of oxy-Hb change in cortices related to visual processing and executive function while distracted with a higher cognitive load; and (d) participants' responses to traffic lights were slower and resulted in a higher activation in prefrontal cortex and occipital areas when distracted by a visual distraction task compared to when distracted with an auditory task; similarly, brain activation increased significantly in temporal areas when participants responded to an auditory car horn task compared to when they responded to visual traffic lights.ConclusionsBoth distracting cognitive load demands and the type of distraction task significantly affect young adult pedestrian performance and threaten pedestrian safety. Pedestrian injury prevention efforts should consider the effects of the type of distracting task and its cognitive demands on pedestrian safety.     

子女越孝顺老年人越幸福吗?老年人孝道期待的作用

孝道是影响老年人幸福感的重要变量之一, 然而, 以往研究却得出相互矛盾的结论, 其中可能的重要原因之一是没有聚焦老年人孝道期待的实现程度。采用二次响应面回归分析探究老年人孝道期待和子女孝道支持行为之间的匹配度对老年人生活满意度和孤独感的影响。研究结果表明, 对于生活满意度而言, 和不匹配相比, 情感期待和情感支持以及联络期待和联络支持匹配时老年人生活满意度更高; 在期待和支持匹配的情况下, 生活满意度随信息期待和信息支持的增加而提高; 并且老年人的生活满意度仅随工具支持的增加而提高, 但与工具期待没有关系。对于孤独感而言, 在情感期待和情感支持二者不匹配时, 较于情感期待低于情感支持, 情感期待高于情感支持时老年人的孤独感更高; 孤独感仅随联络支持和信息支持的增加而降低, 与联络期待、信息期待、工具期待以及工具支持没有关系。该研究得出以下结论：老年人孝道期待的实现程度是提高其生活满意度的重要因素, 而情感期待高于情感支持是影响老年人孤独感的重要因素。