simfd.ed: Simultaneous inference for misaligned functional data in an...

In naolsen/simm.fda: Simultaneous inference for Misaligned Functional Data

Simultaneous inference for misaligned functional data in an exponential family setting

Description

This function applies the simm.fda methodology in a setting of certain exponential models (e.g. poisson) followiong the approach outlined in article[..]

Usage

simfd.ed(y, t, basis_fct, warp_fct, ed_fct, amp_cov = NULL, warp_cov = NULL,
  iter = c(5, 5), w0 = NULL, u0 = NULL, use.nlm = c(FALSE, FALSE),
  suppressLik = FALSE, amp_cov_par = NULL, paramMax = rep(TRUE,
  length(amp_cov_par)), warp_opt = TRUE, like_optim_control = list(),
  design = NULL, inner_parallel = FALSE, save_temp = NULL)

Arguments

y	List of observations. NAs allowed
t	List of corresponding time points. NAs not allowed
basis_fct	Basis function for spline
warp_fct	Warp function
ed_fct	Function defining the exponential family. Must have attribute diff2. See Afkt for examples.
amp_cov	Amplitude covariance function. Must be on the form function(t, param)
warp_cov	Warp covariance function. Must be on the form function(t, param)
iter	two-dimensional integer of maximal number of outer iterations & maximal number of inner iterations per outer iteration.
w0	Starting values for predicted warps. Should only be used if you have results from a previous run.
u0	Starting values for predicted trajectories. Should only be used if you have results from a previous run.
use.nlm	Use nlm instead of optim for optimization? First index for outer loop, second index for inner loop.
suppressLik	Suppress if likelihood has increased
amp_cov_par	Starting values for amplitude covariance parameters. There are no defaults.
paramMax	Logical vector. Which amplitude parameters to optimise over? Defaults to all parameters. May be overwritten by supplying control parameters.
warp_opt	If FALSE, warp covariance parameters are kept fixed.
like_optim_control	List of control options for optimization in outer loop. See ppMulti for details.
design	Design for the experiments. Should be given as a list of one-dimensional vectors or as a design matrix.
inner_parallel	Should the inner optimization be done in parallel?
save_temp	Save estimates after each outer iteration? NULL or the file path.
pr	Printing option.

Details

sim.fd can only handle one-dimensional functional data. It should NOT be applied to Gaussian data, unless sigma^2 is known and fixed beforehand. Not all relevant control parameters have been checked for compliance; however parallelization does work (on Linux)

Value

A list of estimates and predictions of w and u

See Also

ppMulti

naolsen/simm.fda documentation built on June 28, 2022, 2:41 a.m.