Abstract
Causal inference requires an understanding of the conditions under which association equals causation. The exchangeability or no confounding assumption is well known and well understood as central to this task. More recently the epidemiologic literature has described additional assumptions related to the stability of causal effects. In this paper we extend the Sufficient Component Cause Model to represent one expression of this stability assumption--the Stable Unit Treatment Value Assumption. Approaching SUTVA from an SCC model helps clarify what SUTVA is and reinforces the connections between interaction and SUTVA.
Highlights
The potential outcomes approach is becoming the standard for causal inference in epidemiology [1]
We show how the Sufficient Component Cause model can be extended to represent Rubin’s expression of the no interference between units and the no compound versions of treatment assumptions – the Stable Unit Treatment Value Assumption (SUTVA) [7,8]
Sufficient component cause model and response types to depict SUTVA To estimate a precise causal effect of bicycle riding on weight loss in this population, it is assumed that each individual has one potential outcome under the exposed condition and one potential outcome under the unexposed condition
Summary
The potential outcomes approach is becoming the standard for causal inference in epidemiology [1]. The exposure only has an effect on individuals in the second row, labeled the “causal” types Their potential outcomes under exposed and unexposed conditions differ (1-0 = 1) and the exposure has a causal effect for them. Sufficient component cause model and response types to depict SUTVA To estimate a precise causal effect of bicycle riding on weight loss in this population, it is assumed that each individual has one potential outcome under the exposed condition and one potential outcome under the unexposed condition. A precise causal effect in this population, that is the effect of assigning everyone to ride 30 miles a week compared
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call