ctsem (version 3.10.2)

ctStanKalman: Get Kalman filter estimates from a ctStanFit object

Description

Get Kalman filter estimates from a ctStanFit object

Usage

ctStanKalman(
  fit,
  nsamples = NA,
  pointest = TRUE,
  collapsefunc = NA,
  cores = 1,
  subjects = 1:max(fit$standata$subject),
  timestep = "asdata",
  timerange = "asdata",
  standardisederrors = FALSE,
  subjectpars = TRUE,
  tformsubjectpars = TRUE,
  indvarstates = FALSE,
  removeObs = F,
  ...
)

Value

list containing Kalman filter elements, each element in array of iterations, data row, variables. llrow is the log likelihood for each row of data.

Arguments

fit

fit object from ctStanFit.

nsamples

either NA (to extract all) or a positive integer from 1 to maximum samples in the fit.

pointest

If TRUE, uses the posterior mode as the single sample.

collapsefunc

function to apply over samples, such as mean

cores

Integer number of cpu cores to use. Only needed if savescores was set to FALSE when fitting.

subjects

integer vector of subjects to compute for.

timestep

Either a positive numeric value, 'asdata' to use the times in the dataset, or 'auto' to select a timestep automatically (resulting in some interpolation but not excessive computation).

timerange

only relevant if timestep is not 'asdata'. Positive numeric vector of length 2 denoting time range for computations.

standardisederrors

If TRUE, computes standardised errors for prior, upd, smooth conditions.

subjectpars

if TRUE, state estimates are not returned, instead, predictions of each subjects parameters are returned, for parameters that had random effects specified.

tformsubjectpars

if FALSE, subject level parameters are returned in raw, pre transformation form.

indvarstates

if TRUE, do not remove indvarying states from output

removeObs

Logical or integer. If TRUE, observations (but not covariates) are set to NA, so only expectations based on parameters and covariates are returned. If a positive integer N, every N observations are retained while others are set NA for computing model expectations -- useful for observing prediction performance forward further in time than one observation.

...

additional arguments to collpsefunc.

Examples

k=ctStanKalman(ctstantestfit,subjectpars=TRUE,collapsefunc=mean)