结构因果模型框架在生态学观测因果推理中的应用

IF 7.1 1区 环境科学与生态学 Q1 ECOLOGY
Suchinta Arif, M. Aaron MacNeil
{"title":"结构因果模型框架在生态学观测因果推理中的应用","authors":"Suchinta Arif,&nbsp;M. Aaron MacNeil","doi":"10.1002/ecm.1554","DOIUrl":null,"url":null,"abstract":"<p>Ecologists are often interested in answering causal questions from observational data but generally lack the training to appropriately infer causation. When applying statistical analysis (e.g., generalized linear model) on observational data, common statistical adjustments can often lead to biased estimates between variables of interest due to processes such as confounding, overcontrol, and collider bias. To overcome these limitations, we present an overview of structural causal modeling (SCM), an emerging causal inference framework that can be used to determine cause-and-effect relationships from observational data. The SCM framework uses directed acyclic graphs (DAGs) to visualize researchers' assumptions about the causal structure of a system or process under study. Following this, a DAG-based graphical rule known as the backdoor criterion can be applied to determine statistical adjustments (or lack thereof) required to determine causal relationships from observational data. In the presence of unobserved confounding variables, an additional rule called the frontdoor criterion can be employed to determine causal effects. Here, we use simulated ecological examples to review how the backdoor and frontdoor criteria can return accurate causal estimates between variables of interest, as well as how biases can arise when these criteria are not used. We further provide an overview of studies that have applied the SCM framework in ecology. SCM, along with its application of DAGs, has been widely used in other disciplines to make valid causal inferences from observational data. Their use in ecology holds tremendous potential for quantifying causal relationships and investigating a range of ecological questions without randomized experiments.</p>","PeriodicalId":11505,"journal":{"name":"Ecological Monographs","volume":"93 1","pages":""},"PeriodicalIF":7.1000,"publicationDate":"2022-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Applying the structural causal model framework for observational causal inference in ecology\",\"authors\":\"Suchinta Arif,&nbsp;M. Aaron MacNeil\",\"doi\":\"10.1002/ecm.1554\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Ecologists are often interested in answering causal questions from observational data but generally lack the training to appropriately infer causation. When applying statistical analysis (e.g., generalized linear model) on observational data, common statistical adjustments can often lead to biased estimates between variables of interest due to processes such as confounding, overcontrol, and collider bias. To overcome these limitations, we present an overview of structural causal modeling (SCM), an emerging causal inference framework that can be used to determine cause-and-effect relationships from observational data. The SCM framework uses directed acyclic graphs (DAGs) to visualize researchers' assumptions about the causal structure of a system or process under study. Following this, a DAG-based graphical rule known as the backdoor criterion can be applied to determine statistical adjustments (or lack thereof) required to determine causal relationships from observational data. In the presence of unobserved confounding variables, an additional rule called the frontdoor criterion can be employed to determine causal effects. Here, we use simulated ecological examples to review how the backdoor and frontdoor criteria can return accurate causal estimates between variables of interest, as well as how biases can arise when these criteria are not used. We further provide an overview of studies that have applied the SCM framework in ecology. SCM, along with its application of DAGs, has been widely used in other disciplines to make valid causal inferences from observational data. Their use in ecology holds tremendous potential for quantifying causal relationships and investigating a range of ecological questions without randomized experiments.</p>\",\"PeriodicalId\":11505,\"journal\":{\"name\":\"Ecological Monographs\",\"volume\":\"93 1\",\"pages\":\"\"},\"PeriodicalIF\":7.1000,\"publicationDate\":\"2022-09-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ecological Monographs\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/ecm.1554\",\"RegionNum\":1,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ECOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ecological Monographs","FirstCategoryId":"93","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/ecm.1554","RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECOLOGY","Score":null,"Total":0}
引用次数: 7

摘要

生态学家通常对从观测数据中回答因果关系问题感兴趣,但通常缺乏适当推断因果关系的培训。当对观测数据应用统计分析(例如,广义线性模型)时,由于混杂、过度控制和对撞机偏差等过程,常见的统计调整通常会导致感兴趣变量之间的估计存在偏差。为了克服这些局限性,我们概述了结构因果建模(SCM),这是一种新兴的因果推理框架,可用于从观测数据中确定因果关系。SCM框架使用有向无环图(DAG)来可视化研究人员对所研究系统或过程的因果结构的假设。在此之后,可以应用称为后门标准的基于DAG的图形规则来确定从观测数据中确定因果关系所需的统计调整(或缺乏统计调整)。在存在未观察到的混杂变量的情况下,可以采用一种称为前门准则的额外规则来确定因果效应。在这里,我们使用模拟生态示例来回顾后门和前门标准如何在感兴趣的变量之间返回准确的因果估计,以及在不使用这些标准时如何产生偏差。我们进一步概述了在生态学中应用SCM框架的研究。SCM及其DAG的应用已被广泛用于其他学科,从观测数据中进行有效的因果推断。它们在生态学中的应用在量化因果关系和研究一系列生态学问题方面具有巨大的潜力,而无需随机实验。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Applying the structural causal model framework for observational causal inference in ecology

Ecologists are often interested in answering causal questions from observational data but generally lack the training to appropriately infer causation. When applying statistical analysis (e.g., generalized linear model) on observational data, common statistical adjustments can often lead to biased estimates between variables of interest due to processes such as confounding, overcontrol, and collider bias. To overcome these limitations, we present an overview of structural causal modeling (SCM), an emerging causal inference framework that can be used to determine cause-and-effect relationships from observational data. The SCM framework uses directed acyclic graphs (DAGs) to visualize researchers' assumptions about the causal structure of a system or process under study. Following this, a DAG-based graphical rule known as the backdoor criterion can be applied to determine statistical adjustments (or lack thereof) required to determine causal relationships from observational data. In the presence of unobserved confounding variables, an additional rule called the frontdoor criterion can be employed to determine causal effects. Here, we use simulated ecological examples to review how the backdoor and frontdoor criteria can return accurate causal estimates between variables of interest, as well as how biases can arise when these criteria are not used. We further provide an overview of studies that have applied the SCM framework in ecology. SCM, along with its application of DAGs, has been widely used in other disciplines to make valid causal inferences from observational data. Their use in ecology holds tremendous potential for quantifying causal relationships and investigating a range of ecological questions without randomized experiments.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Ecological Monographs
Ecological Monographs 环境科学-生态学
CiteScore
12.20
自引率
0.00%
发文量
61
审稿时长
3 months
期刊介绍: The vision for Ecological Monographs is that it should be the place for publishing integrative, synthetic papers that elaborate new directions for the field of ecology. Original Research Papers published in Ecological Monographs will continue to document complex observational, experimental, or theoretical studies that by their very integrated nature defy dissolution into shorter publications focused on a single topic or message. Reviews will be comprehensive and synthetic papers that establish new benchmarks in the field, define directions for future research, contribute to fundamental understanding of ecological principles, and derive principles for ecological management in its broadest sense (including, but not limited to: conservation, mitigation, restoration, and pro-active protection of the environment). Reviews should reflect the full development of a topic and encompass relevant natural history, observational and experimental data, analyses, models, and theory. Reviews published in Ecological Monographs should further blur the boundaries between “basic” and “applied” ecology. Concepts and Synthesis papers will conceptually advance the field of ecology. These papers are expected to go well beyond works being reviewed and include discussion of new directions, new syntheses, and resolutions of old questions. In this world of rapid scientific advancement and never-ending environmental change, there needs to be room for the thoughtful integration of scientific ideas, data, and concepts that feeds the mind and guides the development of the maturing science of ecology. Ecological Monographs provides that room, with an expansive view to a sustainable future.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信