MétaCan
Menu
Back to cohort
Record W4415059812 · doi:10.1080/10705511.2025.2559270

Controlling for Large Sets of Measured Confounders in Mediation Analysis: Comparison of Bayesian Model Averaging, the LASSO, and Path Analysis

2025· article· en· W4415059812 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueStructural Equation Modeling A Multidisciplinary Journal · 2025
Typearticle
Languageen
FieldMathematics
TopicAdvanced Causal Inference Techniques
Canadian institutionsUniversité LavalMcGill University
FundersNatural Sciences and Engineering Research Council of CanadaFonds de recherche du Québec
KeywordsBayesian probabilityPath analysis (statistics)Path (computing)Bayesian inferenceConfoundingMediation

Abstract

fetched live from OpenAlex

Mediation analysis identifies intermediate variables that transmit the effect from an independent (explanatory) variable to the outcome (response) variable. Ignoring relevant confounders can lead to biased estimates of effect in causal mediation analysis. However, including many confounders in the model may increase the variance of estimators. This paper compares the bias, efficiency, power, Type I error rates, and coverage for causal effects in the single mediator model using path analysis, the LASSO, and Bayesian Model Averaging (BMA). Results show that path analysis yielded unbiased estimates with adequate coverage and Type I error rates, and that BMA and the LASSO yielded higher power than path analysis but encountered instances of excessive bias and Type I error rate when confounder effects on the variables are small. An example from the PROsetta Stone project demonstrates the application of all methods.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.519
Threshold uncertainty score0.571

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.169
GPT teacher head0.449
Teacher spread0.281 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it