四参数Logistic加权模型下被试能力稳健估计

设计项目参数、被试得分已知的测验情境,在两、三、四参数Logistic加权模型下进行能力估计,发现被试得分等级之间的能力步长存在着均匀的步长间距,被试得分能较好的反映多级记分的分数加权作用。两参数Logistic加权模型下会出现被试参数估计扰动现象,猜测现象会导致能力高估现象,失误现象会导致能力低估现象;三参数Logistic加权模型c型下能力高估现象未出现或不明显;三参数Logistic加权模型γ型下能力低估现象未出现或不明显;四参数Logistic加权模型下被试能力高估现象和低估现象都未出现或不明显,四参数Logistic加权模型是被试能力稳健性估计较好的方法。     

改进3PL模型参数估计的MCMC算法

本文首先用马尔科夫链蒙特卡洛(MCMC)算法和EM算法进行IRT模型参数估计模拟实验,并探讨了两种算法的参数估计精度,然后在分析三参数Logistic(3PL)模型参数估计精度的基础上改进模型并对其进行参数估计。结果表明,MCMC算法估计IRT模型的参数精度均优于EM算法,并且MCMC算法在估计3PL模型参数方面具有更明显的优势;在样本量较小的情况下,MCMC算法能较好地估计3PL模型参数,估计精度略低于2PL模型;3PL模型的项目参数确定性低是参数估计精度略低于2PL模型的主要原因;采用改进模型可以提高项目参数的确定性,进而得到更优的参数估计精度。     

CAT中能力参数估计方法的改进:R-MLE估计法

本文对CAT中能力估计的常用方法——最大似然估计法(MLE)进行改进,研究中结合EAP方法提出了改进的MLE法(R-MLE)。Monte Carlo模拟研究发现:不论是在定长CAT还是非定长CAT中,不论是在1PL模型下还是在2PL或3PL模型中,不论是在何种CAT题库结构下,R-MLE法较传统的MLE法具有更佳的估计精度及更有效的测验效率;R-MLE法不仅可以提高CAT的能力估计精度还可以进一步改善CAT测试的效率,具有一定的应用前景。     

多水平随机中介效应估计及其比较

本文在综述各类多水平中介模型的基础上, 聚焦于自变量、中介变量、因变量都来自多水平结构中较低水平的多水平随机中介效应模型, 通过蒙特卡洛模拟研究比较该模型与简化的多水平固定中介效应模型、传统中介效应模型的差别, 并考察了目前用于多水平随机中介效应的三种参数估计方法：限制性极大似然、极大似然、最小方差二次无偏估计在不同情况下对随机中介效应估计的优劣。研究结果显示：当数据符合多水平随机中介效应模型时, 使用简化模型将错误估计中介效应及其标准误, 得到不正确的统计检验结果; 使用多水平随机中介效应模型能够实现对中介效应的正确估计和检验, 其中限制性极大似然或极大似然估计方法优于最小方差二次无偏估计方法。     

当结构假设和分布假设不满足时的验证性因子分析:稳健极大似然估计和贝叶斯估计的比较研究（英文）

结构方程模型已被广泛应用于心理学、教育学、以及社会科学领域的统计分析中。结构方程模型分析中最常用的估计方法是基于正态分布的估计量,比如极大似然估计法。这些方法需要满足两个假设。第一,理论模型必须正确地反映变量与变量之间的关系,称为结构假设。第二,数据必须符合多元正态分布,称为分布假设。如果这些假设不满足,基于正态分布的估计量就有可能导致不正确的卡方指数、不正确的拟合度、以及有偏差的参数估计和参数估计的标准误。在实际应用中,几乎所有的理论模型都不能准确地解释变量与变量之间的关系,数据也常常呈非多元正态分布。为此,一些新的估计方法得以发展。这些方法要么在理论上不要求数据呈多元正态分布,要么对因数据呈非正态分布而导致的不正确结果进行纠正。当前较为流行的两种方法是稳健极大似然估计和贝叶斯估计。稳健极大似然估计是应用Satorra and Bentler(1994)的方法对不正确的卡方指数和参数估计的标准误进行调整,而参数估计和用极大似然方法得出的完全等同。贝叶斯估计方法则是基于贝叶斯定理,其要点是:参数的后验分布是由参数的先验分布和数据似然值相乘而得来。后验分布常用马尔科夫蒙特卡洛算法来进行模拟。对于稳健极大似然估计和贝叶斯估计这两种方法之间的优劣比较,先前的研究只局限于理论模型是正确的情境。而本研究则着重于理论模型是错误的情境,同时也考虑到数据呈非正态分布的情境。本研究所采用的模型是验证性因子模型,数据全部由计算机模拟而来。数据的生成取决于三个因素:8类因子结构,3种变量分布,和3组样本量。这三个因素产生72个模拟条件(72=8x3x3)。每个模拟条件下生成2000个数据组,每个数据组都拟合两个模型,一个是正确模型、一个是错误模型。每个模型都用两种估计方法来拟合:稳健极大似然估计法和贝叶斯估计方法。贝叶斯估计方法中所使用的先验分布是无信息先验分布。结果分析主要着重于模型拒绝率、拟合度、参数估计、和参数估计的标准误。研究的结果表明:在样本量充足的情况下,两种方法得出的参数估计非常相似。当数据呈非正态分布时,贝叶斯估计法比稳健极大似然估计法更好地拒绝错误模型。但是,当样本量不足且数据呈正态分布时,贝叶斯估计在拒绝错误模型和参数估计上几乎没有优势,甚至在一些条件下,比稳健极大似然法要差。     

项目反应理论中潜在心理特质“填补”的参数估计方法及其演变

在心理与教育测量中, 项目反应理论(Item Response Theory, IRT)模型的参数估计方法是理论研究与实践应用的基本工具。最近, 由于IRT模型的不断扩展与EM (expectation-maximization)算法自身的固有问题, 参数估计方法的改进与发展显得尤为重要。这里介绍了IRT模型中边际极大似然估计的发展, 提出了它的阶段性特征, 即联合极大似然估计阶段、确定性潜在心理特质“填补”阶段、随机潜在心理特质“填补”阶段, 重点阐述了它的潜在心理特质“填补” (data augmentation)思想。EM算法与Metropolis-Hastings Robbins-Monro (MH-RM)算法作为不同的潜在心理特质“填补”方法, 都是边际极大似然估计的思想跨越。目前, 潜在心理特质“填补”的参数估计方法仍在不断发展与完善。     

当结构假设和分布假设不满足时的验证性因子分析：稳健极大似然法估计和贝叶斯估计的比较研究

结构方程模型已被广泛应用于心理学、教育学、以及社会科学领域的统计分析中。结构方程模型分析中最常用的估计方法是基于正 态分布的估计量,比如极大似然估计法。这些方法需要满足两个假设。第一, 理论模型必须正确地反映变量与变量之间的关系,称为结构假 设。第二,数据必须符合多元正态分布,称为分布假设。如果这些假设不满足,基于正态分布的估计量就有可能导致不正确的卡方指数、不 正确的拟合度、以及有偏差的参数估计和参数估计的标准误。在实际应用中,几乎所有的理论模型都不能准确地解释变量与变量之间的关系, 数据也常常呈非多元正态分布。为此,一些新的估计方法得以发展。这些方法要么在理论上不要求数据呈多元正态分布,要么对因数据呈非 正态分布而导致的不正确结果进行纠正。当前较为流行的两种方法是稳健极大似然估计和贝叶斯估计。稳健极大似然估计是应用 Satorra and Bentler (1994) 的方法对不正确的卡方指数和参数估计的标准误进行调整,而参数估计和用极大似然方法得出的完全等同。贝叶斯估计方法则是 基于贝叶斯定理,其要点是：参数的后验分布是由参数的先验分布和数据似然值相乘而得来。后验分布常用马尔科夫蒙特卡洛算法来进行模拟。 对于稳健极大似然估计和贝叶斯估计这两种方法之间的优劣比较,先前的研究只局限于理论模型是正确的情境。而本研究则着重于理论模型 是错误的情境,同时也考虑到数据呈非正态分布的情境。本研究所采用的模型是验证性因子模型,数据全部由计算机模拟而来。数据的生成 取决于三个因素：8 类因子结构,3 种变量分布,和3 组样本量。这三个因素产生72 个模拟条件（72=8x3x3）。每个模拟条件下生成2000 个 数据组,每个数据组都拟合两个模型,一个是正确模型、一个是错误模型。每个模型都用两种估计方法来拟合：稳健极大似然估计法和贝叶 斯估计方法。贝叶斯估计方法中所使用的先验分布是无信息先验分布。结果分析主要着重于模型拒绝率、拟合度、参数估计、和参数估计的 标准误。研究的结果表明：在样本量充足的情况下,两种方法得出的参数估计非常相似。当数据呈非正态分布时,贝叶斯估计法比稳健极大 似然估计法更好地拒绝错误模型。但是,当样本量不足且数据呈正态分布时,贝叶斯估计在拒绝错误模型和参数估计上几乎没有优势,甚至 在一些条件下,比稳健极大似然法要差。     

应用项目反应理论对瑞文测验联合型的分析

使用BILOG-MG3.0软件,边际极大似然估计,3参数Logistic模型对354名不同能力水平的男性青年的瑞文测验联合型数据进行了分析。结果显示:大多数瑞文测验联合型的题目都适合3参数Logistic模型(有6道题不适合)。整个测验的信息函数峰值的位置在难度量表的-3到-2之间,其值为16.82。共有18道题的信息函数峰值在0.2以下。从区分度来看,72道题目的区分度均大于0.5,比较理想。难度参数显示所有题目均较低,绝大部分都在0以下,最高的只有1.01。题目的难度主要由所需的操作水平决定。伪猜测参数在0.07-0.24之间。综合分析表明瑞文测验联合型对正常青年的智力评价精度较差。     

多维项目反应理论等级反应模型

基于因子分析和单维项目反应理论的多维项目反应理论是测量理论的新发展方向之一。但是, 多维项目反应理论仍处于不成熟的发展阶段, 多数研究也只是以二级评分为主。本文首先介绍了逻辑斯蒂形式的多维等级反应模型, 并以二维等级反应模型为例, 分析了模型的数学函数图像及其性质。然后, 推导出了多维等级反应模型的项目信息函数, 并结合实例进行了讨论。进一步地, 本文阐述了使用联合极大似然估计和马尔科夫链蒙特卡洛方法估计多维等级反应模型参数的思想。最后, 指出了一些有待研究的问题。     

矩阵取样设计中的似真值能力估计方法

矩阵取样是大规模教育评估中最有效的一种数据收集方式。本研究采用模拟数据考察在均衡的不完全分块（BIB）矩阵取样设计中,似真值（PV）与传统的极大似然估计（MLE）、加权极大似然估计（WLE）和贝叶斯后验期望估计（EAP）方法对学生能力总体参数估计的精确性和稳健性。结果表明,PV对总体平均数和标准差的估计最为精确和稳健;EAP倾向于低估,MLE和WLE倾向于高估,且精确性和稳健性远远不如PV。同时,总被试量对估计结果的影响很小,而每个题本中的项目数量对估计结果的影响较大。     

Together – apart: in touch in a time of separation

This paper explores the experience of working as a Jungian analyst through the various phases of the global COVID-19 pandemic, examining the importance of the physical containing space alongside the analyst’s internal mind and how technology can both help and hinder understanding. A number of clinical vignettes illustrate the challenge of communicating over a distance, paying particular attention to the way countertransference phenomena can become re-attuned. Reference is made to mythology and symbols of hope, and consideration given to the meaning and purpose of the pandemic.     

The Possibility of Meaning in Human Evolution

Science undermines the certitude of non-naturalistic answers to the question of whether human life has meaning. I explore whether evolution can provide a naturalistic basis for existential meaning. Using the work of philosopher Daniel Dennett and scientist Ursula Goodenough, I argue that evolution is the locus of the possibility of meaning because it has produced intentionality, the matrix of consciousness. I conclude that the question of the meaning of human life is an existentialist one: existential meaning is a product of the individual and collective tasks human beings undertake.     

Phenotypic plasticity and archetype: a response to common objections to the biological theory of archetype and instinct

Since Jung’s death in 1961, scholars have attempted to integrate growing biological science data into Jungian concepts such as the collective unconscious, instincts and the archetypes. This enterprise has been challenging due to persistent false dichotomies of gene and environment occasionally arising. Recent works by Roesler (2022a, 2022b) for example, have raised objections to the biological theory of archetypes, but the objections are plagued by such dichotomies. The concept of phenotypic plasticity, however, helps to both avoid this problem as well as bridge the gap between competing theories into a more integrated model with solid biological foundations.     

When is it time to stop? When good enough becomes bad enough

This article draws on Winnicott’s concept of the good enough mother to discuss how to know whether a therapeutic situation is good enough to continue or bad enough to end. This dilemma is explored in terms of clinical syndromes, such as anorexia and pathological gambling, but focuses mainly on analyst-initiated endings, which are termed the ‘Casablanca dilemma’, based on an amplification of the ending of the film Casablanca. The author goes on to discuss such one-sided endings, drawing on interviews with 40 analysts and therapists about their clinical experience. A typology of bad enough endings is presented. The psychological differences between a good enough analysis as opposed to a bad enough one are explored through the ideas of Winnicott and Neumann.     

Kann Es Ein Argument Für Den Skeptizismus Geben? Das Epistemische Problem Der Irrtumsmöglichkeit

Summary  Is there any argument for scepticism? The epistemic problem of the possibility of error. Arguments for scepticism rest on the assumption that knowledge claims are fallible. For this reason the concept of knowledge appears to be questionable. Since it is necessary to distinguish doubts from possible doubts, the arguments for scepticism appear to be unconvincing. If we take it into account that we know something that is immune to doubt, we should draw the conclusion that, contrary to scepticism, knowledge claims have to be compatible with being fallible. Thus any knowledge claim is capable of being doubted.     

The transcendent function in Spitteler’s Prometheus and Epimetheus

In August 2020, John Beebe and Steve Myers met via Zoom to discuss their differing interpretations of psychological typology and the different sources within Jung’s writings that influenced their books: Integrity in Depth: Energies and Patterns in Psychological Type (Beebe), and Myers-Briggs Typology vs Jungian Individuation (Myers). The discussion centred on Spitteler’s epic poem Prometheus und Epimetheus, which forms the basis of chapter V of Psychological Types. This is both the largest chapter and one of two chapters that Jung highlighted in the Argentine foreword as containing the essence of the book. Jung’s book is primarily about the transformation of personality rather than the categorization of people. Although it contains a critical psychology that deconstructs the nature of consciousness, that is only one half of the book and a stepping-stone to the other half, which is the reconciliation of opposites with particular emphasis on the relation of consciousness and the unconscious. Jung assumed that readers were already familiar with Prometheus und Epimetheus, an understanding of which sheds light on the nature of the transformation that Jung described – the development of a new attitude towards attitude itself.     

Chapter 6: Biblical Foundations for a Practical Theology of Aging

SUMMARY

This article reviews Biblical sources pertaining to the elderly, particularly the frail elderly. Founded on these sources, implications for elderly with Alzheimer's Disease and other forms of dementia are addressed through a personal perspective informed by writings of Christian mystics.     

Seeing in the Dark: A View into Dissociation and Healing

In this paper, I will explore the role of art-making, the experience of trauma and dissociation, and the process of working with self-states from an analytic and creative frame. Relevant literature on dissociation, trauma, and the use of art will be discussed. A case involving my work with an adolescent girl who had experienced sexual abuse from a family member will be shared, with an emphasis on the meaningful role images played during the therapeutic process. Both Jungian and psychoanalytic models of conceptualizing and working with dissociation are included, following Donald Kalsched’s (2013) recommendation for a “binocular stance” to treatment, including both a focus on the inner, intrapsychic world and the interpersonal, relational realm, and how art images both illuminated and expressed these realms. Within the therapeutic process, art images allowed the therapist a view into the client’s unconscious process, and created a meeting ground for dissociative barriers to be gradually seen, felt and known, by both therapist and client. The experience of dissociation, in images and in session, provided a reference point for myself and my client, Taylor, to develop a shared understanding and a framework for growth.