实验心理病理学家的贝叶斯分析入门
A Primer on Bayesian Analysis for Experimental Psychopathologists.
作者信息
Krypotos Angelos-Miltiadis, Blanken Tessa F, Arnaudova Inna, Matzke Dora, Beckers Tom
机构信息
Utrecht University.
Netherlands Institute for Neuroscience.
出版信息
J Exp Psychopathol. 2017;8(2):140-157. doi: 10.5127/jep.057316.
Abstract
The principal goals of experimental psychopathology (EPP) research are to offer insights into the pathogenic mechanisms of mental disorders and to provide a stable ground for the development of clinical interventions. The main message of the present article is that those goals are better served by the adoption of Bayesian statistics than by the continued use of null-hypothesis significance testing (NHST). In the first part of the article we list the main disadvantages of NHST and explain why those disadvantages limit the conclusions that can be drawn from EPP research. Next, we highlight the advantages of Bayesian statistics. To illustrate, we then pit NHST and Bayesian analysis against each other using an experimental data set from our lab. Finally, we discuss some challenges when adopting Bayesian statistics. We hope that the present article will encourage experimental psychopathologists to embrace Bayesian statistics, which could strengthen the conclusions drawn from EPP research.
摘要
实验精神病理学（EPP）研究的主要目标是深入了解精神障碍的致病机制，并为临床干预的发展提供坚实基础。本文的主要观点是，采用贝叶斯统计比继续使用零假设显著性检验（NHST）能更好地实现这些目标。在文章的第一部分，我们列出了NHST的主要缺点，并解释了为什么这些缺点限制了从EPP研究中得出的结论。接下来，我们强调贝叶斯统计的优点。为了说明这一点，我们使用实验室的一个实验数据集将NHST和贝叶斯分析进行对比。最后，我们讨论采用贝叶斯统计时面临的一些挑战。我们希望本文能鼓励实验精神病理学家接受贝叶斯统计，这可以加强从EPP研究中得出的结论。
相似文献
1
A Primer on Bayesian Analysis for Experimental Psychopathologists.实验心理病理学家的贝叶斯分析入门
J Exp Psychopathol. 2017;8(2):140-157. doi: 10.5127/jep.057316.
2
Bayesian analysis for nurse and midwifery research: statistical, practical and ethical benefits.护士与助产研究中的贝叶斯分析：统计、实践及伦理方面的益处
Nurse Res. 2023 Jan 19. doi: 10.7748/nr.2023.e1852.
3
Bayesian alternatives for common null-hypothesis significance tests in psychiatry: a non-technical guide using JASP.精神医学中常见的虚无假设显著性检验的贝叶斯替代方法：使用 JASP 的非技术性指南。
BMC Psychiatry. 2018 Jun 7;18(1):178. doi: 10.1186/s12888-018-1761-4.
4
Bayesian inference of population prevalence.贝叶斯推断种群流行率。
Elife. 2021 Oct 6;10:e62461. doi: 10.7554/eLife.62461.
5
Bayesian alternatives to null hypothesis significance testing in biomedical research: a non-technical introduction to Bayesian inference with JASP.贝叶斯替代零假设检验在生物医学研究中的应用：使用 JASP 进行贝叶斯推理的非技术性介绍
BMC Med Res Methodol. 2020 Jun 5;20(1):142. doi: 10.1186/s12874-020-00980-6.
6
An Introduction to Calculating Bayes Factors in JASP for Speech, Language, and Hearing Research.JASP 中用于言语、语言和听觉研究的贝叶斯因子计算简介。
J Speech Lang Hear Res. 2019 Dec 10;62(12):4523-4533. doi: 10.1044/2019_JSLHR-H-19-0183. Print 2019 Dec 18.
7
fbst: An R package for the Full Bayesian Significance Test for testing a sharp null hypothesis against its alternative via the e value.fbst：一个 R 包，用于全贝叶斯显著性检验，通过 e 值对尖锐零假设与其备择假设进行检验。
Behav Res Methods. 2022 Jun;54(3):1114-1130. doi: 10.3758/s13428-021-01613-6. Epub 2021 Sep 1.
8
Complementing the P-value from null-hypothesis significance testing with a Bayes factor from null-hypothesis Bayesian testing.用零假设贝叶斯检验的贝叶斯因子对零假设显著性检验的P值进行补充。
Nurse Res. 2020 Nov 4. doi: 10.7748/nr.2020.e1756.
9
To P or Not to P: Backing Bayesian Statistics.支持还是反对P值：支持贝叶斯统计。
Otolaryngol Head Neck Surg. 2017 Dec;157(6):915-918. doi: 10.1177/0194599817739260.
10
Beyond p-values in the evaluation of brain-computer interfaces: A Bayesian estimation approach.脑机接口评估中超越p值：一种贝叶斯估计方法。
J Neurosci Methods. 2016 Sep 1;270:30-45. doi: 10.1016/j.jneumeth.2016.06.008. Epub 2016 Jun 15.
引用本文的文献
1
Attitudes towards depression and its treatment among white, hispanic, and multiracial adults.白人、西班牙裔和多种族成年人对抑郁症及其治疗的态度。
BMC Psychol. 2024 Aug 14;12(1):441. doi: 10.1186/s40359-024-01804-8.
2
Beyond regression: Unpacking research of human complex systems with qualitative comparative analysis.超越回归：用定性比较分析剖析人类复杂系统的研究
Heliyon. 2024 May 16;10(10):e31457. doi: 10.1016/j.heliyon.2024.e31457. eCollection 2024 May 30.
3
Far from the threatening crowd: Generalisation of conditioned threat expectancy and fear in COVID-19 lockdown.远离威胁人群：COVID-19 封锁期间条件性威胁预期和恐惧的泛化。
Learn Behav. 2024 Sep;52(3):262-271. doi: 10.3758/s13420-024-00625-4. Epub 2024 Jan 29.
4
Racial discrimination predicts mental health outcomes beyond the role of personality traits in a community sample of African Americans.在非裔美国人的社区样本中，种族歧视对心理健康结果的预测作用超过了人格特质的影响。
Clin Psychol Sci. 2021 Mar;9(2):183-196. doi: 10.1177/2167702620957318. Epub 2021 Feb 12.
5
Phonological Working Memory and Sentence Production in School-Age Children with Typical Language, Dyslexia, and Comorbid Dyslexia and Developmental Language Disorder.学龄期儿童典型语言、阅读障碍、阅读障碍与发育性语言障碍共病者的语音工作记忆与句子生成。
J Child Lang. 2024 Jan;51(1):56-90. doi: 10.1017/S0305000922000435. Epub 2022 Oct 19.
6
The deviation-from-familiarity effect: Expertise increases uncanniness of deviating exemplars.偏离熟悉度效应：专业知识增加了偏离范例的诡异感。
PLoS One. 2022 Sep 1;17(9):e0273861. doi: 10.1371/journal.pone.0273861. eCollection 2022.
7
Methodological implications of sample size and extinction gradient on the robustness of fear conditioning across different analytic strategies.样本量和灭绝梯度对不同分析策略下恐惧条件反射稳健性的方法学意义。
PLoS One. 2022 May 24;17(5):e0268814. doi: 10.1371/journal.pone.0268814. eCollection 2022.
8
Applying hierarchical bayesian modeling to experimental psychopathology data: An introduction and tutorial.应用分层贝叶斯模型于实验心理病理学数据：介绍与教程。
J Abnorm Psychol. 2021 Nov;130(8):923-936. doi: 10.1037/abn0000707.
9
Enhanced Matching of Children's Faces in "Super-Recognisers" But Not High-Contact Controls.“超级识别者”中儿童面部的匹配能力增强，但高接触对照组则不然。
Iperception. 2020 Jul 26;11(4):2041669520944420. doi: 10.1177/2041669520944420. eCollection 2020 Jul-Aug.
10
Reducing the Emotionality of Auditory Hallucination Memories in Patients Suffering From Auditory Hallucinations.降低患有幻听症患者幻听记忆的情绪化程度
Front Psychiatry. 2019 Sep 18;10:637. doi: 10.3389/fpsyt.2019.00637. eCollection 2019.
本文引用的文献
1
Is There a Free Lunch in Inference?推理中存在免费的午餐吗？
Top Cogn Sci. 2016 Jul;8(3):520-47. doi: 10.1111/tops.12214.
2
Default Bayes Factors for Model Selection in Regression.回归模型选择中的默认贝叶斯因子
Multivariate Behav Res. 2012 Nov;47(6):877-903. doi: 10.1080/00273171.2012.734737.
3
Sequential hypothesis testing with Bayes factors: Efficiently testing mean differences.贝叶斯因子的序贯假设检验：高效检验均值差异。
Psychol Methods. 2017 Jun;22(2):322-339. doi: 10.1037/met0000061. Epub 2015 Dec 14.
4
The fallacy of placing confidence in confidence intervals.对置信区间寄予信任的谬误。
Psychon Bull Rev. 2016 Feb;23(1):103-23. doi: 10.3758/s13423-015-0947-8.
5
Bayesian Assessment of Null Values Via Parameter Estimation and Model Comparison.贝叶斯方法通过参数估计和模型比较来评估缺失值。
Perspect Psychol Sci. 2011 May;6(3):299-312. doi: 10.1177/1745691611406925.
6
Statistical Evidence in Experimental Psychology: An Empirical Comparison Using 855 t Tests.实验心理学中的统计证据：使用 855 个 t 检验的实证比较。
Perspect Psychol Sci. 2011 May;6(3):291-8. doi: 10.1177/1745691611406923.
7
Bayesian Versus Orthodox Statistics: Which Side Are You On?贝叶斯统计与经典统计：你站在哪一边？
Perspect Psychol Sci. 2011 May;6(3):274-90. doi: 10.1177/1745691611406920.
8
Analyzing small data sets using Bayesian estimation: the case of posttraumatic stress symptoms following mechanical ventilation in burn survivors.使用贝叶斯估计分析小数据集：烧伤幸存者机械通气后创伤后应激症状的案例。
Eur J Psychotraumatol. 2015 Mar 11;6:25216. doi: 10.3402/ejpt.v6.25216. eCollection 2015.
9
Using Bayes to get the most out of non-significant results.贝叶斯推断在不显著结果中的应用。
Front Psychol. 2014 Jul 29;5:781. doi: 10.3389/fpsyg.2014.00781. eCollection 2014.
10
Do CS-US pairings actually matter? A within-subject comparison of instructed fear conditioning with and without actual CS-US pairings.条件刺激-非条件刺激配对真的重要吗？对有和没有实际条件刺激-非条件刺激配对的指令性恐惧条件作用进行的一项被试内比较。
PLoS One. 2014 Jan 23;9(1):e84888. doi: 10.1371/journal.pone.0084888. eCollection 2014.
Zotero 插件