SPECIOUS CAUSAL ATTRIBUTIONS IN THE SOCIAL-SCIENCES - THE REFORMULATED STEPPING-STONE THEORY OF HEROIN USE AS EXEMPLAR
SPECIOUS CAUSAL ATTRIBUTIONS IN THE SOCIAL-SCIENCES - THE REFORMULATED STEPPING-STONE THEORY OF HEROIN USE AS EXEMPLAR
复制标题
DOI：
10.1037/0022-3514.45.6.1289
复制
发表时间：
1983-01-01
影响因子：
7.6
通讯作者：
BAUMRIND, D
中科院分区：
文献类型：
--
作者：
BAUMRIND, D
基于使用统计或实验控制的因果模型来检验这些主张。当应用于社会或行为科学数据时，这种说法被发现是过度的。在一个典型的案例中，强烈的因果声明是基于原因的正则性模型的弱版本而提出的，本文对此进行了批评。Ja O‘Donnell和RR Clayton(见Record 1983-32937-001)声称，要确定大麻的使用是海洛因使用的一个原因(他们的“重新制定的垫脚石”假说)，必须且充分地证明大麻的使用先于海洛因的使用，并且当剔除被认为在这两个因素之前的其他变量的影响时，这两种药物的使用之间在统计学上的显著联系不会消失。本文认为，O‘Donnell和Clayton版本的规律性模型不足以确定原因，而社会干预的计划既假设也需要生成性因果模型，而不是规律性因果模型。使用统计控制的因果建模是有价值的，当它迫使调查人员做出明确的因果解释并证明其合理性时，而不是当它被提供作为因果关系的生成性分析的替代品时。(参考文献41)(心理信息数据库记录(C)2016 APA，版权所有)
Examines the claims based on causal models employing either statistical or experimental controls. Such claims were found to be excessive when applied to social or behavioral science data. An exemplary case, in which strong causal claims are made on the basis of a weak version of the regularity model of cause, is critiqued. JA O'Donnell and RR Clayton (see record 1983-32937-001) claim that to establish that marihuana use is a cause of heroin use (their" reformulated stepping-stone" hypothesis), it is necessary and sufficient to demonstrate that marihuana use precedes heroin use and that the statistically significant association between use of the 2 drugs does not vanish when the effects of other variables deemed to be prior to both of them are removed. Here, it is argued that O'Donnell and Clayton's version of the regularity model is not sufficient to establish cause and that the planning of social interventions both presumes and requires a generative rather than a regularity causal model. Causal modeling using statistical controls is of value when it compels the investigator to make explicit and to justify a causal explanation but not when it is offered as a substitute for a generative analysis of causal connection.(41 ref)(PsycINFO Database Record (c) 2016 APA, all rights reserved)