Discrete Exponential-Family Models for Multivariate Binary Outcomes

arXiv · 2022

Studies that collect multi-outcome data such as tobacco and alcohol use are becoming increasingly common.

Work in progress2022

  1. Vega Yon, G. G.UofUiD
  2. Pugh, M. J.UofU
  3. Valente, T. W.USC

DOI•Publisher / Preprint•arXiv• Code

Abstract

Studies that collect multi-outcome data such as tobacco and alcohol use are becoming increasingly common. In principle, multi-outcomes studies investigate the correlations between outcomes, including, causal links and/or joint distributions. Although there are many methods for studying multivariate outcomes, significant limitations regarding scale and interpretation persist. Here we introduce a model based on the exponential-family for discrete binary outcomes that provides a flexible framework for hypothesis testing of multiple binary outcomes in a computationally efficient fashion.

Cite

@misc{vegayonDiscreteExponentialFamilyModels2022,
  title = {Discrete Exponential-Family Models for Multivariate Binary Outcomes},
  author = {{Vega Yon}, {George G.} and {Pugh}, {Mary Jo} and {Valente}, {Thomas W.}},
  year = {2022},
  month = {11},
  publisher = {arXiv},
  number = {arXiv:2211.00627},
  doi = {10.48550/arXiv.2211.00627},
  url = {https://arxiv.org/abs/2211.00627},
}

← All research