贝叶斯因子及其在JASP中的实现

统计推断在科学研究中起到关键作用, 然而当前科研中最常用的经典统计方法——零假设检验(Null hypothesis significance test, NHST)却因难以理解而被部分研究者误用或滥用。有研究者提出使用贝叶斯因子(Bayes factor)作为一种替代和(或)补充的统计方法。贝叶斯因子是贝叶斯统计中用来进行模型比较和假设检验的重要方法, 其可以解读为对零假设H₀或者备择假设H₁的支持程度。其与NHST相比有如下优势：同时考虑H₀和H₁并可以用来支持H₀、不“严重”地倾向于反对H₀、可以监控证据强度的变化以及不受抽样计划的影响。目前, 贝叶斯因子能够很便捷地通过开放的统计软件JASP实现, 本文以贝叶斯t检验进行示范。贝叶斯因子的使用对心理学研究者来说具有重要的意义, 但使用时需要注意先验分布选择的合理性以及保持数据分析过程的透明与公开。     

评估零效应的三种统计方法CSSCI

在心理学研究中,研究者可能需要评估效应是否不存在,但常用的原假设显著性检验无法提供支持零效应的证据。因此,实践中研究者要么对p>0.05的情况进行回避,要么错误地认为p>0.05支持了原假设。近年来,等价检验、贝叶斯估计和贝叶斯因子逐渐被用于评估零效应。文章介绍了这三种方法的原理,并通过两个实例分析,展示三种方法的实际应用。这三种评估零效应的方法能够帮助心理学研究者在实际研究中进行合理的统计推断和研究决策。     

新世纪20年国内假设检验及其关联问题的方法学研究

新世纪20年来国内假设检验方法学研究内容可分为如下几类: 零假设显著性检验的不足、p值的使用问题、心理学研究的可重复性问题、效应量、检验力、等效性检验、其他与假设检验关联的研究。零假设显著性检验已经发展成一套组合流程: 为了保证检验力和节省成本, 实验研究需要做先验检验力分析预估样本容量, 但问卷超过160人在传统统计中就没有必要这样做。当拒绝零假设时, 应当结合效应量做出结论。当不拒绝零假设时, 需要报告后验检验力; 如果效应量中或大而检验力不够高, 则可增加被试再行分析, 但这一过程应主动披露, 报告最后的实际p值并对可能犯的第一类错误率做出评估。     

心理研究中引入贝叶斯统计推断的必要性、应用思路与领域

本文从科学范式演变和概率统计推断特征分析出发,就贝叶斯统计推断引入心理学的必要性、怎么应用、在哪些领域应用集中进行了论述。首先在分析科学范式演进各阶段统计推断任务需要、经典的频率概率统计推断不足基础上,得出科学范式处于危机和革命阶段时需要对相关理论做可信度检验。然后,在介绍贝叶斯定理及其统计推断的基础上,进一步分析了贝叶斯推断能解决理论可信度的多种假设检验情景。最后本文还就贝叶斯统计推断在心理学理论争鸣与建构、心理技术产品开发与评估具体领域应用做了分析。     

心理研究引入贝叶斯统计推断的必要性、应用思路与领域

本文从科学范式演变和概率统计推断特征分析出发,就贝叶斯统计推断引入心理学的必要性、怎么应用、在哪些领域应用进行了论述。首先在分析科学范式演进各阶段统计推断任务需要、经典的频率概率统计推断不足基础上,得出科学范式处于危机和革命阶段时需要对相关理论做可信度检验。然后,在介绍贝叶斯定理及其统计推断的基础上,进一步分析了贝叶斯推断能解决理论可信度的多种假设检验情景。最后本文还就贝叶斯统计推断在心理学理论争鸣与建构、心理技术产品开发与评估具体领域应用做了分析。     

心理学中对假设检验一些批评的分析

根据假设检验原理的贝叶斯统计的表达方式分析和回应了心理学中对传统的假设检验方法的主要批评.认为:(1)确定假设的接受域不仅要考虑,同时也应该考虑以及这个假设的先验概率,而元分析方法的提出可看作对先验概率考虑的必然的逻辑结果;(2)零假设是可以接受的,但它的接受域只是备掸假设接受域余集的一个子集;(3)传统的假设检验方法需要其他方法的补充.     

跳出传统假设检验方法的陷阱——贝叶斯因子在心理学研究领域的应用

近年来,心理学研究者逐渐认识到假设检验这一推论统计方法在理论与实践中的不足。在心理学研究面对日益严重的"可重复危机"、急需更优良的验证手段时,贝叶斯因子分析在众多统计方法中脱颖而出。相比传统的假设检验方法,贝叶斯因子具有诸多优势,能够揭示备择假设与虚无假设成立可能性的高低,因此心理学界也出现了以贝叶斯因子分析取代传统假设检验的呼声。本文列举了贝叶斯因子相对于假设检验的主要优势,并重点介绍了贝叶斯因子在常规心理学研究中的计算方法及应用,同时说明了运用贝叶斯因子进行统计分析时需注意的问题。     

基于一般线性模型框架的心理统计教学

心理统计学教学中,不同的统计方法常常是独立教学,致使学生不易理解各种方法之间的关系。事实上,t检验、方差分析和多元线性回归等方法都可以统一到一般线性模型的框架下,而结构方程是对这个框架的最一般化的描述,且结构方程路径图是呈现这个框架的形象工具。因此,本文尝试用路径图的方式来呈现心理学研究中最常用的统计方法,并将结构方程分析结果与传统分析结果进行对照,帮助学生建立一般线性模型上位概念,将以往孤立的统计方法联系起来。     

Q矩阵包含错误的诊断测验分类准确性比较

Q矩阵是认知诊断测验的重要组成部分之一,围绕Q矩阵构建的诊断模型对Q矩阵中包含的错误较敏感。贝叶斯网分类模型是基于网络结点之间的关系构建的模型,将朴素贝叶斯网作为诊断模型,与DINA模型进行比较。模拟实验结果表明：Q矩阵中是否包含可达矩阵和错误界定的项目数量对DINA模型影响较大,对贝叶斯网模型影响较小;项目数量对DINA和贝叶斯网模型影响都较大;样本大小对贝叶斯网模型影响较大,对DINA模型影响较小。模拟研究结果显示,当Q矩阵中不包含可达阵、包含5个以上错误项目或样本数较大时,贝叶斯网分类模型优于DINA模型;而当Q矩阵中包含可达阵和5个(以下)错误项目时,DINA模型优于贝叶斯分类模型。     

贝叶斯统计方法的应用与现状

贝叶斯统计方法是心理学数据分析的热门方法。研究全面论述贝叶斯方法在心理学领域的应用与方向。现阶段贝叶斯方法以模拟研究为主,应用方向为心理学研究常用的项目反应理论、认知诊断、计算机自适应、结构方程模型。同时,评述发现贝叶斯方法正逐步被国内心理学研究者所接受。最后,文章讨论了当下贝叶斯统计在心理学研究中应用的局限性及可能的原因,建议统计学者开发界面友好的贝叶斯软件,并在心理学课程中加入贝叶斯知识。     

Bayes factor approaches for testing interval null hypotheses

Psychological theories are statements of constraint. The role of hypothesis testing in psychology is to test whether specific theoretical constraints hold in data. Bayesian statistics is well suited to the task of finding supporting evidence for constraint, because it allows for comparing evidence for 2 hypotheses against each another. One issue in hypothesis testing is that constraints may hold only approximately rather than exactly, and the reason for small deviations may be trivial or uninteresting. In the large-sample limit, these uninteresting, small deviations lead to the rejection of a useful constraint. In this article, we develop several Bayes factor 1-sample tests for the assessment of approximate equality and ordinal constraints. In these tests, the null hypothesis covers a small interval of non-0 but negligible effect sizes around 0. These Bayes factors are alternatives to previously developed Bayes factors, which do not allow for interval null hypotheses, and may especially prove useful to researchers who use statistical equivalence testing. To facilitate adoption of these Bayes factor tests, we provide easy-to-use software.     

期刊简介

《心理学报》,月刊,中国心理学会和中国科学院心理研究所主办,科学出版社出版,主要发表我国心理学家最新、最高水平的心理学科技论文。1956年创刊。作为反映我国心理学研究水平的主要窗口,《心理学报》不仅在中国心理学界享有较高的声誉,在国际上也有一定影响。在国际上,《心理学报》是SCOPUS(Elsevier),ESCI(Emerging Sources Citations Index,Web of Science),PsycINFO/Psychological Abstracts(APA)等重要数据库的检索(收录)期刊。     

期刊简介

《心理学报》,月刊,中国心理学会和中国科学院心理研究所主办,科学出版社出版,主要发表我国心理学家最新、最高水平的心理学科技论文。1956年创刊。作为反映我国心理学研究水平的主要窗口,《心理学报》不仅在中国心理学界享有较高的声誉,在国际上也有一定影响。在国际上,《心理学报》是SCOPUS(Elsevier),ESCI(Emerging Sources Citations Index,Web of Science),PsycINFO/Psychological Abstracts(APA)等重要数据库的检索(收录)期刊。在国内,《心理学报》是国家科技部《中国科技论文统计源期刊》(CSTPCD);中国科学引文数据库(CSCD)核心期刊;中国科学文献计量评价研究中心(中国科学院文献情报中心、中国社会科学院文献信息中心、中国学术期刊<光盘版>电子杂志社、北京大学图书馆)《中国科学引文数据库》来源期刊、《中国人文社会科学引文数据库》来源期刊、《中国学术期刊综合评价数据库》来源期刊;中国社会科学院文献信息中心《中国人文社会科学核心期刊》;南京大学社会科学数据库研究开发中心《中文社会科学引文索引(CSSCI)》统计源期刊;《中国学术期刊文摘》源期刊;被北京地区高校期刊工作研究会和北京大学图书馆选录为心理学类核心期刊,编入《中文核心期刊要目总览》(2020年版)。     

社区感的研究现状（1977～2020）及展望——基于Leximancer的内容分析

社区感是社区心理学领域中最重要的概念之一。全面系统地呈现社区感研究的主题及核心概念,探讨演进趋势及中国场景中的特殊性,对推进我国社区感研究的本土化发展具有重要意义。研究以系统筛查后的644篇SSCI文献的标题及摘要作为分析文本,采用内容分析法对不同阶段及中国本土研究中所呈现的关键主题及核心概念进行阐述和分析。研究结果表明社区感的研究对象以城市居民及学生群体为主; 研究方法主要以实证的问卷调查展开; 社区感的前因变量和结果变量中包含了健康、满意度、邻里关系、生活质量等因素; 社区感研究在不同的发展阶段及中国场景中所关注的话题均有其独特性。基于研究结果,本研究针对社区感的未来发展提供了若干建议,旨在推进社区感在中国本土实践场景下的发展。     

Our neoliberal fantasies? A preliminary test of research trends in leading journals in work and organizational psychology

Prior to engaging in a substantive discussion on the supposed influence of neoliberalism on research in work and organizational psychology (WOP), it is important to verify the empirical basis of the trends advanced by Bal and Dóci (Neoliberal ideology in work and organizational psychology, European Journal of Work and Organizational Psychology [Online First Publication, 2018]). To this end, we content analysed 745 abstracts of empirical studies published in leading WOP journals during the years 2006–2007 and 2016–2017. Results of our content analysis do not support the hypothesized trends towards more instrumentality and individualism in WOP research, suggesting that Bal and Dóci’s (2018) portrayal of the WOP literature does not provide a solid basis for discussion. On the basis of our findings, we conclude with recommendations to broaden the scope of WOP research to also include macro-level, societal issues.     

Parsing strategies and discourse context

Two experiments investigated syntactic processing during comprehension of sentences presented either in isolation or in a discourse context. Comprehension of a range of different types of surface structurally ambiguous sentences was studied. To explain the interpretations generally given to the sentences processed in isolation, two parsing principles were proposed: Kimball's (1973) Right Association and Verb Dominance. When the ambiguous sentences were read in context, the interpretations computed were still determined by these structurally based principles, even when this meant that the meanings were at variance with the prior context. These results indicate that surface structure parsing of sentences proceeds in the same way whether sentences are processed alone or in context.This research was supported by a grant from the Australian Research Grants Scheme. I thank Linda Cupples for her help in conducting the experiments and in analyzing the data. I am indebted to Marilyn Ford for her critical comments on an earlier, version of the article. Thanks are also due to Dianne Bradley, Ken Forster, and Roger Wales for their helpful comments on the topic.     

Qualitative research in psychology: Could William James get a job?

Considering the case of William James, the author examines the likelihood of a successful career as a qualitative researcher in contemporary U.S. psychology. Fifty-seven journals affiliated with the American Psychological Association or its divisions were analyzed to show the place of qualitative research in U.S. psychology over the past 50 years. Journal abstracts, mission statements, and a short e-mail questionnaire from editors were used to understand patterns and trends in qualitative research in U.S. psychology. Editors are generally accepting of qualitative work, although mission statements do not always signal likely interest in qualitative work. The amount of qualitative work published is comparably low, but patterns of increased publication are found in some journals. Trends in methodologies, topics of research, and ways in which qualitative research enters journals over time are discussed. Suggestions for the publication of qualitative work are provided.     

Evaluating the evidence base for relational frame theory: a citation analysis

Relational frame theory (RFT) is a contemporary behavior-analytic account of language and cognition. Since it was first outlined in 1985, RFT has generated considerable controversy and debate, and several claims have been made concerning its evidence base. The present study sought to evaluate the evidence base for RFT by undertaking a citation analysis and by categorizing all articles that cited RFT-related search terms. A total of 174 articles were identified between 1991 and 2008, 62 (36%) of which were empirical and 112 (64%) were nonempirical articles. Further analyses revealed that 42 (68%) of the empirical articles were classified as empirical RFT and 20 (32%) as empirical other, whereas 27 (24%) of the nonempirical articles were assigned to the nonempirical reviews category and 85 (76%) to the nonempirical conceptual category. In addition, the present findings show that the majority of empirical research on RFT has been conducted with typically developing adult populations, on the relational frame of sameness, and has tended to be published in either The Psychological Record or the Journal of the Experimental Analysis of Behavior. Overall, RFT has made a substantial contribution to the literature in a relatively short period of time.     

On the Stability of Psychological Hardiness: A Three-Year Longitudinal Study

More than 30 years of research has established psychological hardiness as an important individual resiliency resource. One important question still remaining is whether psychological hardiness can be trained. The present study explored this question longitudinally within the context of a 3-year military academy training program. Cadets from 3 different Norwegian military academies (N = 293) completed hardiness questionnaires during the first week of their training, and then again at the end of each year, resulting in a total of 4 waves of data. Using hierarchical linear modeling, no statistically significant effect of time on hardiness scores was found. The nonsignificant growth parameter was examined further using Bayesian statistics as an indicator of the relative evidence for the null hypothesis of no change over time versus the alternative hypothesis of change. The resulting Bayes factor provided substantial support in our data for the null hypothesis of no hardiness development during the 3-year officer training programs.