fdp_staplmer.fit: Functional Dirichlet Process Spatial Temporal Aggregated...

View source: R/fdp_staplmer.R

fdp_staplmer.fitR Documentation

Functional Dirichlet Process Spatial Temporal Aggregated Predictor Linear Mixed Effects Regression Model Fit

Description

Functional Dirichlet Process Spatial Temporal Aggregated Predictor Linear Mixed Effects Regression Model Fit

Usage

fdp_staplmer.fit(
  y,
  Z,
  X,
  W,
  subj_mat,
  subj_n,
  weights = rep(1, length(y)),
  alpha_a = 1,
  alpha_b = 1,
  sigma_a = 1,
  sigma_b = 1,
  tau_a = 1,
  tau_b = 1,
  K = 5L,
  rank_one,
  rank_two,
  threshold = 0L,
  iter_max,
  burn_in,
  thin = 1L,
  fix_alpha = FALSE,
  bw = FALSE,
  seed = NULL,
  chain = 1L,
  logging = FALSE
)

Arguments

y

vector of outcomes

Z

design matrix

X

stap design matrix

W

group terms design matrix from glFormula

subj_mat

matrix indexing subject-measurement locations in (Z,X,W)

subj_n

vector of number of subject measurements

weights

weights for weighted regression - default is vector of ones

alpha_a

alpha gamma prior hyperparameter

alpha_b

alpha gamma prior hyperparameter

sigma_a

precision gamma prior hyperparameter

sigma_b

precision gamma prior hyperparameter

tau_a

penalty parameters gamma prior hyperparameter

tau_b

penalty parameters gamma prior hyperparameter

K

truncation number for DP mixture components

rank_one

rank of first smoothing matrix

rank_two

rank of second smoothing matrix

threshold

number of members per cluster at which cluster is included in regression

iter_max

maximum number of iterations

burn_in

number of iterations to burn-in

thin

number by which to thin samples

fix_alpha

boolean value

bw

boolean value indicating whether or not subject decomposition is used

seed

random number generator seed will be set to default value if not by user

chain

chain label

logging

boolean parameter indicating whether or not a single iteration should be run with print messages indicating successful completion of the Sampler's sub modules


apeterson91/rstapDP documentation built on Sept. 20, 2023, 9:34 a.m.