cv_vbvs_concurrent: cv_vbvs_concurrent

In jeff-goldsmith/vbvs.concurrent: Variational Bayes Variable Selection for the Functional Linear Concurrent Model

Description

Cross validation to choose the tuning parameter v0 in the variational bayes variable selection algorithm for the linear functional concurrent model. Uses five-fold cross validation.

Usage

cv_vbvs_concurrent(formula, id.var = NULL, data = NULL, Kt = 5, Kp = 2,
  v0 = seq(0.01, 0.1, 0.01), v1 = 100, SEED = 1, standardized = FALSE,
  t.min = NULL, t.max = NULL)

Arguments

formula	formula for desired regression. should have form y ~ x1 + x2 + ... + x_k | t, where t is the variable that parameterized observed functions
id.var	variable giving subject ID vector
data	optional data frame
Kt	number of spline basis functions for coefficients and FPCs
Kp	number of FPCs to estimate
v0	tuning parameter vector; normal spike variance. defaults to 0.01 to 0.1 in increments of 0.01.
v1	tuning parameter; normal slab variance
SEED	seed value, used to ensure reproducibility of the training split
standardized	logical; are covariates already standardized?
t.min	minimum value to be evaluated on the time domain (useful if data are sparse and / or irregular). if 'NULL', taken to be minimum observed value.
t.max	maximum value to be evaluated on the time domain (useful if data are sparse and / or irregular). if 'NULL', taken to be maximum observed value.

Author(s)

Jeff Goldsmith [e-mail]

jeff-goldsmith/vbvs.concurrent documentation built on Sept. 17, 2019, 2:26 p.m.