Performs full multi-dimensional profile likelihood calculations

Usage

# S3 method for class 'ctsmTMB.fit'
profile(
  fitted,
  parlist,
  grid.size = rep(10, length(parlist)),
  grid.qnt = rep(3, length(parlist)),
  hessian = FALSE,
  silent = FALSE,
  control = list(trace = 0, iter.max = 1000, eval.max = 1000),
  ...
)

Arguments

fitted: a ctmsTMB fit object
parlist: a named-list of parameters to profile over. The user can either supply grid-values in the list or leave it empty. If the any one list is empty then grid-values will be calculated using the estimated parameter mean value and standard deviation.
grid.size: a vector of length(parlist) indicating the number of grid-points along each parameter direction. This is only used if the parlist is empty.
grid.qnt: a vector of length(parlist) determining the width of the grid points from the mean value in multiples of the standard deviation.
hessian: a boolean indicating whether to use the hessian or not during the profile optimization.
silent: boolean whether or not to mute current iteration number the control argument.
control: a list of optimization output controls (see nlminb)
...: various arguments (not in use)

Note

The implementation was modified from that of https://github.com/kaskr/adcomp/blob/master/TMB/R/tmbprofile.R

Examples

library(ctsmTMB)
model <- ctsmTMB$new()

# create model
model$addSystem(dx ~ theta * (mu+u-x) * dt + sigma_x*dw)
model$addObs(y ~ x)
model$setVariance(y ~ sigma_y^2)
model$addInput(u)
model$setParameter(
  theta   = c(initial = 1, lower=1e-5, upper=50),
  mu      = c(initial=1.5, lower=0, upper=5),
  sigma_x = c(initial=1, lower=1e-10, upper=30),
  sigma_y = 1e-2
)
model$setInitialState(list(1,1e-1))

# fit model to data
fit <- model$estimate(Ornstein)
#> Checking model components...
#> Checking and setting data...
#> Constructing objective function and derivative tables...
#> Minimizing the negative log-likelihood...
#>   0:     160.35328:  1.00000  1.50000  1.00000
#>  10:     89.603625:  2.58436  2.91384  1.15608
#> 	 Optimization finished!:
#>             Elapsed time: 0.008 seconds.
#>             The objective value is: 7.387879e+01
#>             The maximum gradient component is: 9.9e-08
#>             The convergence message is: relative convergence (4)
#>             Iterations: 19
#>             Evaluations: Fun: 29 Grad: 20
#>             See stats::nlminb for available tolerance/control arguments.
#> Returning results...
#> Finished!

# calculate profile likelihood
out <- profile(fit,parlist=list(theta=NULL))
#> Iteration: 1 / 10 
#> Iteration: 2 / 10 
#> Iteration: 3 / 10 
#> Iteration: 4 / 10 
#> Iteration: 5 / 10 
#> Iteration: 6 / 10 
#> Iteration: 7 / 10 
#> Iteration: 8 / 10 
#> Iteration: 9 / 10 
#> Iteration: 10 / 10