Premium
Packet randomized experiments for eliminating classes of confounders
Author(s) -
Pavela Greg,
Wiener Howard,
Fontaine Kevin R.,
Fields David A.,
Voss Jameson D.,
Allison David B.
Publication year - 2015
Publication title -
european journal of clinical investigation
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.164
H-Index - 107
eISSN - 1365-2362
pISSN - 0014-2972
DOI - 10.1111/eci.12378
Subject(s) - causal inference , randomization , confounding , randomized controlled trial , observational study , mendelian randomization , random assignment , network packet , research design , restricted randomization , computer science , statistics , medicine , mathematics , biology , computer network , biochemistry , genetic variants , genotype , gene
Background Although randomization is considered essential for causal inference, it is often not possible to randomize in nutrition and obesity research. To address this, we develop a framework for an experimental design—packet randomized experiments ( PRE s), which improves causal inferences when randomization on a single treatment variable is not possible. This situation arises when subjects are randomly assigned to a condition (such as a new roommate) which varies in one characteristic of interest (such as weight), but also varies across many others. There has been no general discussion of this experimental design, including its strengths, limitations, and statistical properties. As such, researchers are left to develop and apply PRE s on an ad hoc basis, limiting its potential to improve causal inferences among nutrition and obesity researchers. Methods We introduce PRE s as an intermediary design between randomized controlled trials and observational studies. We review previous research that used the PRE design and describe its application in obesity‐related research, including random roommate assignments, heterochronic parabiosis, and the quasi‐random assignment of subjects to geographic areas. We then provide a statistical framework to control for potential packet‐level confounders not accounted for by randomization. Results Packet randomized experiments have successfully been used to improve causal estimates of the effect of roommates, altitude, and breastfeeding on weight outcomes. When certain assumptions are met, PRE s can asymptotically control for packet‐level characteristics. This has the potential to statistically estimate the effect of a single treatment even when randomization to a single treatment did not occur. Conclusions Applying PRE s to obesity‐related research will improve decisions about clinical, public health, and policy actions insofar as it offers researchers new insight into cause and effect relationships among variables.