genMCMC_star_ispline {countSTAR} | R Documentation |
MCMC sampler for STAR with a monotone spline model for the transformation
Description
Run the MCMC algorithm for STAR given
a function to initialize model parameters; and
a function to sample (i.e., update) model parameters.
The transformation is modeled as an unknown, monotone function using I-splines. The Robust Adaptive Metropolis (RAM) sampler is used for drawing the parameter of the transformation function.
Usage
genMCMC_star_ispline(
y,
sample_params,
init_params,
lambda_prior = 1/2,
y_max = Inf,
nsave = 5000,
nburn = 5000,
nskip = 0,
save_y_hat = FALSE,
target_acc_rate = 0.3,
adapt_rate = 0.75,
stop_adapt_perc = 0.5,
verbose = TRUE
)
Arguments
y |
|
sample_params |
a function that inputs data
and optionally a fourth element |
init_params |
an initializing function that inputs data |
lambda_prior |
the prior mean for the transformation g() is the Box-Cox function with
parameter |
y_max |
a fixed and known upper bound for all observations; default is |
nsave |
number of MCMC iterations to save |
nburn |
number of MCMC iterations to discard |
nskip |
number of MCMC iterations to skip between saving iterations, i.e., save every (nskip + 1)th draw |
save_y_hat |
logical; if TRUE, compute and save the posterior draws of the expected counts, E(y), which may be slow to compute |
target_acc_rate |
target acceptance rate (between zero and one) |
adapt_rate |
rate of adaptation in RAM sampler (between zero and one) |
stop_adapt_perc |
stop adapting at the proposal covariance at |
verbose |
logical; if TRUE, print time remaining |
Details
If the coefficients list from init_params
and sample_params
contains a named element beta
,
e.g. for linear regression, then the function output contains
-
coefficients
: the posterior mean of the beta coefficients -
post.beta
: draws from the posterior distribution ofbeta
-
post.othercoefs
: draws from the posterior distribution of any other sampled coefficients, e.g. variance terms
If no beta
exists in the parameter coefficients, then the output list just contains
-
coefficients
: the posterior mean of all coefficients -
post.beta
: draws from the posterior distribution of all coefficients
Additionally, if init_params
and sample_params
have output mu_test
, then the sampler will output
post.predtest
, which contains draws from the posterior predictive distribution at test points.
Value
A list with at least the following elements:
-
post.pred
: draws from the posterior predictive distribution ofy
-
post.sigma
: draws from the posterior distribution ofsigma
-
post.log.like.point
: draws of the log-likelihood for each of then
observations -
WAIC
: Widely-Applicable/Watanabe-Akaike Information Criterion -
p_waic
: Effective number of parameters based on WAIC -
post.g
: draws from the posterior distribution of the transformationg
-
post.sigma.gamma
: draws from the posterior distribution ofsigma.gamma
, the prior standard deviation of the transformation g() coefficients -
fitted.values
: the posterior mean of the conditional expectation of the countsy
(NULL
ifsave_y_hat=FALSE
) -
post.fitted.values
: posterior draws of the conditional mean of the countsy
(NULL
ifsave_y_hat=FALSE
)
along with other elements depending on the nature of the initialization and sampling functions. See details for more info.