dodControl: Control settings for the dod function

Description Usage Arguments Value Author(s) See Also Examples

View source: R/dod.R

Description

Specify control setting when fitting the the Thurstonian Degree-of-Difference (DOD) model using dod and dod_fit.

Usage

1
2
3
4
5
6
7
dodControl(grad.tol = 1e-4,
           integer.tol = 1e-8,
           get.vcov = TRUE,
           get.grad = TRUE,
           test.args = TRUE,
           do.warn=TRUE,
           optCtrl=list())

Arguments

grad.tol

tolerance for the maximum absolute gradient of the parameters are convergence.

integer.tol

tolerance for when to give a warning about non-integer counts in data.

get.vcov

compute the variance-covariance matrix of the parameters (and the standard error of d-prime)?

get.grad

compute the gradient of the parameters?

test.args

test admissibility of arguments to dod and dod_fit?

do.warn

if FALSE warnings from the fitting process are suppressed.

optCtrl

control parameters passed on to the nlminb optimizer.

Value

An list of class dodControl with the appropriate control settings for dod and dod_fit.

Author(s)

Rune Haubo B Christensen

See Also

dod, dod_fit, dodSim, dodPwr, optimal_tau,

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
## DOD example data:
same.pairs <- c(25, 22, 33, 20)
diff.pairs <- c(18, 22, 30, 30)

## Fit Thurstonian dod-model and perform difference test:
dod(same=same.pairs, diff=diff.pairs)

## Display the fitting process using the trace argument to nlminb:
ctrl <- dodControl(optCtrl=list(trace=TRUE))
dod(same=same.pairs, diff=diff.pairs, control=ctrl)

sensR documentation built on Feb. 11, 2020, 1:10 a.m.