What question did this study set out to answer?

To develop structured Bayesian variable selection strategies within joint models linking high-dimensional, mixed-type longitudinal predictors to a binary health outcome.

August 16, 2026Statistical Methods in Medical Research

Bayesian variable selection for joint models of heterogeneous longitudinal variables and a binary outcome

View Full Paper

Ask AI

Bookmark

Authors

LSLingpeng Shan MNMichelle J. Naughton EPElectra D. Paskett

Discussion

Member takes

Overview

Methodological study demonstrates robust predictor identification for post-treatment insomnia in breast cancer survivors, indicating enhanced statistical power in high-dimensional analyses.

Key Points

To develop structured Bayesian variable selection strategies within joint models linking high-dimensional, mixed-type longitudinal predictors to a binary health outcome.
Formulated two Bayesian variable selection approaches: single-level selection for the binary outcome (JM1) and simultaneous two-level selection across longitudinal trajectories and outcomes (JM2).
Incorporated shrinkage priors to control overfitting from high-dimensional predictors and adapted false discovery rate-based rules to evaluate multi-part models with grouped categorical variables.
Applied the framework to analyze clinical and lifestyle trajectories from the Women's Health Initiative and Life and Longevity After Cancer study.
The JM2 framework successfully performed simultaneous variable selection across longitudinal trajectories and binary outcomes while managing high-dimensional interactions.
The model identified a critical predictor of post-treatment insomnia in breast cancer survivors that conventional analytical approaches failed to detect.

Cite This Study

Shan et al. (2026) studied this question.

synapsesocial.com/papers/6a8179bcf2fb91fc834acfa4 https://doi.org/10.1177/09622802261478572

View Full Paper

Ask AI

Bookmark

August 16, 2026Statistical Methods in Medical Research

Bayesian variable selection for joint models of heterogeneous longitudinal variables and a binary outcome

View Full Paper

Ask AI

Bookmark

Authors

LSLingpeng Shan MNMichelle J. Naughton EPElectra D. Paskett

Discussion

Member takes

Overview

Methodological study demonstrates robust predictor identification for post-treatment insomnia in breast cancer survivors, indicating enhanced statistical power in high-dimensional analyses.

Key Points

To develop structured Bayesian variable selection strategies within joint models linking high-dimensional, mixed-type longitudinal predictors to a binary health outcome.
Formulated two Bayesian variable selection approaches: single-level selection for the binary outcome (JM1) and simultaneous two-level selection across longitudinal trajectories and outcomes (JM2).
Incorporated shrinkage priors to control overfitting from high-dimensional predictors and adapted false discovery rate-based rules to evaluate multi-part models with grouped categorical variables.
Applied the framework to analyze clinical and lifestyle trajectories from the Women's Health Initiative and Life and Longevity After Cancer study.
The JM2 framework successfully performed simultaneous variable selection across longitudinal trajectories and binary outcomes while managing high-dimensional interactions.
The model identified a critical predictor of post-treatment insomnia in breast cancer survivors that conventional analytical approaches failed to detect.

Cite This Study

Shan et al. (2026) studied this question.

synapsesocial.com/papers/6a8179bcf2fb91fc834acfa4 https://doi.org/10.1177/09622802261478572

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark