oscar-package: oscar: Optimal Subset Cardinality Regression

In oscar: Optimal Subset Cardinality Regression (OSCAR) Models Using the L0-Pseudonorm

oscar: Optimal Subset Cardinality Regression

Description

OSCAR models utilize the L0-pseudonorm to select an optimal subset of features that generalizes linear regression models to a variety of families. Currently supported models include conventional Gaussian regression (family="mse" or family="gaussian"), Binomial/Logistic regression (family="logistic"), and Cox proportional hazards modeling (family="cox").

References

Halkola AS, Joki K, Mirtti T, Mäkelä MM, Aittokallio T, Laajala TD (2023) OSCAR: Optimal subset cardinality regression using the L0-pseudonorm with applications to prognostic modelling of prostate cancer. PLoS Comput Biol 19(3): e1010333. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1371/journal.pcbi.1010333")}

oscar documentation built on Oct. 2, 2023, 5:08 p.m.