Naive regression requires weaker assumptions than factor models to adjust for multiple cause confounding.
Justin GrimmerDean KnoxBrandon M. StewartPublished in: J. Mach. Learn. Res. (2023)
Keyphrases
- simplifying assumptions
- data sets
- learning algorithm
- prior knowledge
- regression methods
- regression model
- regression analysis
- classification and regression problems
- database
- accurate models
- multiple models
- gaussian processes
- factor analysis
- linear model
- statistical models
- experimental data
- process model
- maximum likelihood
- probability distribution
- probabilistic model
- case study