ind_fun_NLfP: the log-marginal likelhood function based on the invers...

In BayesS5: Bayesian Variable Selection Using Simplified Shotgun Stochastic Search with Screening (S5)

Description

a log-marginal likelhood value of a model, based on the peMoM prior on the regression coefficients and inverse gamma prior (0.01,0.01) on the variance.

Usage

ind_fun_NLfP(ind2, y, phi, n, p, K, IP.phi, C.prior1, tuning)

Arguments

ind2	the index of covariates in a model
y	the response variable
phi	the B-spline basis
n	the sample size
p	the total number of covariates
K	the degree of freedom for the B-spline basis
IP.phi	the projection matrix on the null space; Q matrix in Shin and Bhattacharya (2020+)
C.prior1	the logarithm of the normalizing constant of the nonlocal funcitonal prior
tuning	a value of the tuning parameter

References

Shin, M. and Bhattacharya, A.(2020) Nonlocal Functional Priors for Nonparametric Hypothesis Testing and High-dimensional Model Selection.

BayesS5 documentation built on March 26, 2020, 7:14 p.m.