The Gaussian Graphical Model in Cross-Sectional and Time-Series Data

We discuss the Gaussian graphical model (GGM; an undirected network of partial correlation coefficients) and detail its utility as an exploratory data analysis tool. The GGM shows which variables predict one-another, allows for sparse modeling of covariance structures, and may highlight potential causal relationships between observed variables. We describe the utility in three kinds of psychological data sets: data sets in which consecutive cases are assumed independent (e.g., cross-sectional data), temporally ordered data sets (e.g., n = 1 time series), and a mixture of the 2 (e.g., n > 1 time series). In time-series analysis, the GGM can be used to model the residual structure of a vector-autoregression analysis (VAR), also termed graphical VAR. Two network models can then be obtained: a temporal network and a contemporaneous network. When analyzing data from multiple subjects, a GGM can also be formed on the covariance structure of stationary means—the between-subjects network. We discuss the interpretation of these models and propose estimation methods to obtain these networks, which we implement in the R packages graphicalVAR and mlVAR. The methods are showcased in two empirical examples, and simulation studies on these methods are included in the supplementary materials.     

The linguistic organization of public controversy: A note on the pragmatics of political discourse

Conclusion This paper does not mean to imply that it is only public controversy that can meaningfully affect political outcomes, or even that it is the most important factor. Rather, we have attempted to indicate that public controversy constitutes a forum on which political actorsact; on which they attempt to implicate each other and the public in terms of some preferred view of the controversy at hand. It is certainly the case that the formal structure of the government and power relationships provides important constraints in terms of which controversy may take place. Yet within these constraints, actors can meaningfully construct various views of the structure of the controversy which differently construe the rights and obligations of participants. In this sense, the course of public controversy may in part be understood as a function of the language employed by these actors, both to the extent that particular expressions stand as documentary evidence of underlying discrepancies about the shape of the controversy and to the extent that the logic of certain speech-acts constrains the forms subsequent statements may take.     

Children's Use of Social Conceptions: Toward a Dynamic Model of Social Cognition

For developmental social psychology to be clinically practical, it must use categories of experience similar to categories that counselors, clinicians, and other practitioners find useful. Knowledge of the developmental forms or levels, conceptions of critical issues in intrapsychic (individual), friendship, and peer group relationships provide such a map of how individuals at different ages view their social relations. The article also describes how individuals may function at different levels depending on the context in which they are expressing their understanding (e.g., spontaneous discussion, reflective thought).     

Common functional principal components analysis: a new approach to analyzing human movement data

In many human movement studies angle-time series data on several groups of individuals are measured. Current methods to compare groups include comparisons of the mean value in each group or use multivariate techniques such as principal components analysis and perform tests on the principal component scores. Such methods have been useful, though discard a large amount of information. Functional data analysis (FDA) is an emerging statistical analysis technique in human movement research which treats the angle-time series data as a function rather than a series of discrete measurements. This approach retains all of the information in the data. Functional principal components analysis (FPCA) is an extension of multivariate principal components analysis which examines the variability of a sample of curves and has been used to examine differences in movement patterns of several groups of individuals. Currently the functional principal components (FPCs) for each group are either determined separately (yielding components that are group-specific), or by combining the data for all groups and determining the FPCs of the combined data (yielding components that summarize the entire data set). The group-specific FPCs contain both within and between group variation and issues arise when comparing FPCs across groups when the order of the FPCs alter in each group. The FPCs of the combined data may not adequately describe all groups of individuals and comparisons between groups typically use t-tests of the mean FPC scores in each group. When these differences are statistically non-significant it can be difficult to determine how a particular intervention is affecting movement patterns or how injured subjects differ from controls. In this paper we aim to perform FPCA in a manner allowing sensible comparisons between groups of curves. A statistical technique called common functional principal components analysis (CFPCA) is implemented. CFPCA identifies the common sources of variation evident across groups but allows the order of each component to change for a particular group. This allows for the direct comparison of components across groups. We use our method to analyze a biomechanical data set examining the mechanisms of chronic Achilles tendon injury and the functional effects of orthoses.     

Assessing individual differences in categorical data

In cognitive modeling, data are often categorical observations taken over participants and items. Usually subsets of these observations are pooled and analyzed by a cognitive model assuming the category counts come from a multinomial distribution with the same model parameters underlying all observations. It is well known that if there are individual differences in participants and/or items, a model analysis of the pooled data may be quite misleading, and in such cases it may be appropriate to augment the cognitive model with parametric random effects assumptions. On the other hand, if random effects are incorporated into a cognitive model that is not needed, the resulting model may be more flexible than the multinomial model that assumes no heterogeneity, and this may lead to overfitting. This article presents Monte Carlo statistical tests for directly detecting individual participant and/or item heterogeneity that depend only on the data structure itself. These tests are based on the fact that heterogeneity in participants and/or items results in overdispersion of certain category count statistics. It is argued that the methods developed in the article should be applied to any set of participant 3 item categorical data prior to cognitive model-based analyses.     

When transference isn't transference: Iatrogenesis of multiple role relations between practicing therapists

Charismatic, grandiose and authoritarian senior therapists often develop complicated relationships not only with practicing therapists who are their colleagues, but also their friends, supervisees, as well as patients. The patient/therapist in a multiple role relationship with such a senior person may be extremely vulnerable and very unaware of the true nature of the problem Under certain conditions, some of these patient/therapists have suffered ego dysfunction and decompensation which appeared to be iatrogenic in origin rather than due to the patient's transference resistance. The implications of these issues for the field of psychotherapy, and underlying dynamics in vulnerable patient/therapist's, and in grandiose, narcissistic group leaders, are highlighted, along with ways of identifying the intrapsychic, interpersonal, and institutional roots of this problem An earlier draft of this paper was presented at the 1990 Meeting of the American Group Psychotherapy Association in Boston.     

The Observation of Incremental Validity Does Not Always Mean Unique Contribution to Prediction

Statistical analyses require proper interpretation. Misinterpretation leads to a lack of understanding of the relationships among variables. Worse, it can lead to misunderstanding of these relationships, which sometimes lead researchers and practitioners to infer the presence of a source of variance that is not present. This is especially true in regression where increased predictiveness from an additional variable may be due to either common or specific variance. In many instances, erroneous interpretation leads to erroneous attribution of the source of the improved prediction. Three examples are provided and methods for detecting specific variance are suggested.     

Educational risk factors for psychological truancy in Lesotho: a qualitative exploration

A qualitative case study design was used to explore educational risk factors that may contribute to psychological truancy in a Lesotho secondary school. Purposively sampled teachers (n = 4, females = 50%) and pupils (n = 4, females = 75%), who have experience of psychological truancy, took part in a focus group and individual interviews. Inductive content analysis was used to analyse data emanating from the interviews. The findings indicate that pupil–teacher relationships, the use of English as medium of instruction and a lack of resources may be educational risk factors contributing to psychological truancy. Positive pupil–teacher relationships and active classroom engagement are prerequisites for successful and active learning.     

Introduction

A dynamic model of affect suggests that positive and negative affect (PA and NA) are normally relatively independent of one another, whereas the heightened apprehensiveness and narrowed cognitive attention in persons with anxiety may contribute to a more unidimensional affect structure. This possibility was examined in a sample of 230 patients seeking treatment for anxiety and depressive disorders in the Netherlands. Two methods, a multiple-group confirmatory factor analysis (CFA) and Fisher's z test of correlations, were used to test these predicted relationships within a sample of persons diagnosed with either a depressive or an anxiety disorder. Both methods supported these predictions, with the depressed group exhibiting relatively independent PA and NA while the anxious group's affects were more strongly inversely correlated.     

SHOULD MARITAL RELATIONS BE NON‐HIERARCHICAL?

The paper explores an egalitarian norm widely accepted today, which I call the Marital Non‐Hierarchy Standard. According to this standard, marital relationships should be non‐hierarchical; neither partner may be more dominant than the other. The Marital Non‐Hierarchy Standard is exceptional: in almost all associations, including many financial, professional, educational and recreational ones, in almost all spheres of life, some hierarchies, within certain limits, are widely believed to be morally legitimate. I argue that in marital relations, too, some hierarchies should be accepted as morally legitimate. It might be argued that marital relations should be loving, and love requires that lovers will have the same degree of power. However, contemporary analyses of love show that love is consistent with (some) hierarchies. It might also be argued that justice requires that lovers will have equal power. However, theories of distributive justice such as Rawls's, Sen's, Dworkin's, and almost all others allow some marital hierarchies. Thus, both the love requirement and the justice requirement allow some hierarchical marital relationships and conflict with the Marital Non‐Hierarchy Standard. Until other justifications for this standard are presented, it is unclear why it should be endorsed.     

How accurate are women's estimates of date of onset of next menses?

Abstract

Because of individual differences in Occurrence of ovulation and patterns of hormonal secretions, one would usually prefer to measure locus in the menstrual cycle using physiological assessment procedures. But such methods are time consuming and costly. When exploring a new domain for possible relations to the menstrual cycle, it would be cost effective to use the simpler procedure of having each women verbally estimate date of onset of next menses. The accuracy of such estimates was studied in two college age samples. Estimated number of days until next onset correlated highly with actual number of days, as verified by follow-up (r = 0.90). As a group, women neither under- nor overestimated number of days. The precision with which these judgments were made was reasonably high. In sum, when a group of women are followed for one cycle, the average accuracy is very high, certainly high enough to support use of such verbal reports for certain scientific purposes.     

Dynamic analyses of mother-child interactions in functional and dysfunctional dyads: a synergetic approach

Describes the application of a new analytical approach (derived from synergetics, a complex dynamic systems theory) to home observational data of mother–child interactions in average dyads and dyads with children referred for disruptive behavior problems at home and school (n = 11 in each group). Results show that (1) the two groups differed in their daily interactions in predictable ways, and (2) the most frequent patterns of interactions observed in the two groups brought them back repeatedly to behave in similar ways toward each other. The findings are in keeping with a body of literature on mother–child interactions. However, they add to it by providing multivariate, graphical representations of these interactions and by offering a conceptual framework within which to move from an observational to an inferential level of analysis. At that level, the transactional processes that are characteristic of functional and dysfunctional relationships may become apparent.     

问题解决测验中过程数据的特征抽取与能力评估

基于计算机的问题解决测验可以实时记录被试探索环境和解决问题时的详细行动痕迹,并保存为过程数据。首先介绍了过程数据的分析流程,然后从问题解决测验入手,分别对过程数据的特征抽取和能力估计建模两方面的研究进行了梳理和评价。未来研究应注意：提高分析结果的可解释性;特征提取时纳入更多信息;实现更复杂问题情景下的能力评估;注重方法的实用性;以及融合与借鉴不同领域的分析方法。     

Correcting an analysis of variance for clustering

A great deal of educational and social data arises from cluster sampling designs where clusters involve schools, classrooms, or communities. A mistake that is sometimes encountered in the analysis of such data is to ignore the effect of clustering and analyse the data as if it were based on a simple random sample. This typically leads to an overstatement of the precision of results and too liberal conclusions about precision and statistical significance of mean differences. This paper gives simple corrections to the test statistics that would be computed in an analysis of variance if clustering were (incorrectly) ignored. The corrections are multiplicative factors depending on the total sample size, the cluster size, and the intraclass correlation structure. For example, the corrected F statistic has Fisher's F distribution with reduced degrees of freedom. The corrected statistic reduces to the F statistic computed by ignoring clustering when the intraclass correlations are zero. It reduces to the F statistic computed using cluster means when the intraclass correlations are unity, and it is in between otherwise. A similar adjustment to the usual statistic for testing a linear contrast among group means is described.     

The analysis of variance and covariance techniques in relation to the conventional formulas for the standard error of a difference

In this paper it is demonstrated that the analysis of variance techniques yield results equivalent to the calculation oft by means of expressions based on the short or the long formula. It is also shown that the covariance technique gives results equivalent to those obtained by means of the formula fort which should be used with matched groups. The conditions necessary for equivalent results are such that the conventional formulas fort would normally be used rather than the variance or covariance techniques. However, a knowledge of the relationships described in this paper should contribute to one's understanding of the variance and covariance techniques.The relationships described in this paper were brought to the attention of the author by the excellent article of Eugene Shen (8). The proofs given here and the examples are the work of the present author.     

心理学研究数据类型与统计方法——谈函数型数据分析的引入

心理学研究数据大致分为截面数据、时间序列数据和面板数据, 三种数据类型的分析方法及使用前提因数据属性不同而有所不同。心理学截面数据的统计方法过于依赖模型的线性结构和假设条件等, 在处理心理学面板数据中难以充分发挥统计方法的功用。函数型数据分析方法主要适用于面板数据处理, 特别适宜ERP、fMRI、发展心理等心理实验中存在时间序列的面板数据的统计分析, 为心理学研究提供了有力的新工具。     

The concept of evolution and revolution

We hypothesize that there exist certain similarities between the strategies adopted by a biological organism, an individual or a social group, when faced by an aggressor. These strategies consist in either minimizing the aggression or else combating it immediately, in order to preserve, in the short term, the identity of the system under attack. One of the strategies commonly adopted for this purpose is retrocession, permitting the biological, neurobiological organism, or the social individual or group to elude certain environmental elements and return to a situation in which other escape routes may be taken.

In the long term, preservation of the external identity is accomplished by modification of the internal identity. Man uses in vivo or, after “extrusion,” ex vivo immunizing and cognitive functions to cope with the environment. He is thus able to create, ex vivo, therapeutic techniques by manipulating internal identity. In order to accomplish this, a profound knowledge is needed, at the level of each individual, of the functional mechanisms of biological and neurobiological identities.

Though social and biological sciences are progressing, they have great difficulties in finding the common language necessary to communicate productively. Analogies between these two domains, that we shall attempt to illustrate, may contribute to facilitating such communication.     

A latent profile analysis of the Five Factor Model of personality: Modeling trait interactions

Interactions among the dimensions of the Five Factor Model (FFM) have not typically been evaluated in mental health research, with the extant literature focusing on bivariate relationships with psychological constructs of interest. This study used latent profile analysis to mimic higher-order interactions to identify homogenous personality profiles using the FFM, and also examined relationships between resultant profiles and affect, self-esteem, depression, anxiety, and coping efficacy. Participants (N = 371) completed self-report and daily diary questionnaires. A 3-profile solution provided the best fit to the data; the profiles were characterized as well-adjusted, reserved, and excitable. The well-adjusted group reported better psychological functioning in validation analyses. The reserved and excitable groups differed on anxiety, with the excitable group reporting generally higher anxiety than the reserved group. Latent profile analysis may be a parsimonious way to model personality heterogeneity.