def_tune: Define tuning parameters for regularization during...

In USCbiostats/LUCid: Latent Unknown Clustering with Integrated Data

Description

Defines selection options and tuning parameters in est_lucid, sem_lucid fitting.

Usage

def_tune(
  Rho_G = -9,
  Rho_Z_InvCov = 0,
  Rho_Z_CovMu = 0,
  Select_G = FALSE,
  Select_Z = FALSE
)

Arguments

Rho_G	Penalty for selection on genetic data, numeric, default is -9 using a sequence of penalties
Rho_Z_InvCov	Penalty for the inverse of covariance of biomarkers, numeric, default is 0
Rho_Z_CovMu	Penalty for the product of covariance and mean of biomarkers, numeric, default is 0
Select_G	Flag to do model selection on genetic data, default is FALSE
Select_Z	Flag to do model selection on biomarker data, default is FALSE

Value

A list of tuning parameters and settings will be returned for integrative clustering.

Author(s)

Cheng Peng, Zhao Yang, David V. Conti

USCbiostats/LUCid documentation built on Feb. 22, 2020, 8:57 p.m.