Create a '>config_Shadow object for Shadow Test Assembly (STA).
createShadowTestConfig(
item_selection = NULL,
content_balancing = NULL,
MIP = NULL,
MCMC = NULL,
refresh_policy = NULL,
exposure_control = NULL,
stopping_criterion = NULL,
interim_theta = NULL,
final_theta = NULL,
theta_grid = seq(-4, 4, 0.1),
audit_trail = F
)A list containing item selection criteria.
method The type of criteria. Accepts one of MFI, MPWI, FB, EB.
info_type The type of information. Accepts FISHER.
initial_theta Initial theta value(s) for the first item selection.
fixed_theta Fixed theta value(s) to optimize for all items to select.
A list containing content balancing options.
method The type of balancing method. Accepts one of NONE, STA.
A list containing solver options.
solver The type of solver. Accepts one of lpsymphony, Rsymphony, gurobi, lpSolve, Rglpk.
verbosity Verbosity level.
time_limit Time limit to be passed onto solver. Used in solvers lpsymphony, Rsymphony, gurobi, Rglpk.
gap_limit Gap limit (relative) to be passed onto solver. Used in solver gurobi. Uses the solver default when NULL.
gap_limit_abs Gap limit (absolute) to be passed onto solver. Used in solver lpsymphony, Rsymphony. Uses the solver default when NULL.
A list containing Markov-chain Monte Carlo configurations.
burn_in Numeric. The number of chains from the start to discard.
post_burn_in Numeric. The number of chains to use after discarding the first burn_in chains.
thin Numeric. Thinning interval.
jumpfactor Numeric. Jump factor.
A list containing refresh policy for obtaining a new shadow test.
method The type of policy. Accepts one of ALWAYS, POSITION, INTERVAL, THRESHOLD, INTERVAL-THRESHOLD, STIMULUS, SET, PASSAGE.
interval Integer. Set to 1 to refresh at each position, 2 to refresh at every two positions, and so on.
threshold Numeric. The shadow test is refreshed when the absolute change in theta estimate is greater than this value.
position Numeric. Position(s) at which refresh to occur.
A list containing exposure control settings.
method Accepts one of "NONE", "ELIGIBILITY", "BIGM", "BIGM-BAYESIAN".
M Big M constant.
max_exposure_rate Maximum target exposure rate.
acceleration_factor Acceleration factor.
n_segment Number of theta segments.
first_segment Theta segment assumed at the begining of test.
segment_cut A numeric vector of segment cuts.
initial_eligibility_stats A list of eligibility statistics from a previous run.
fading_factor Fading factor.
diagnostic_stats TRUE to generate diagnostic statistics.
A list containing stopping criterion.
method Accepts one of "FIXED".
test_length Test length.
min_ni Maximum number of items to administer.
max_ni Minumum number of items to administer.
se_threshold Standard error threshold for stopping.
A list containing interim theta estimation options.
method The type of estimation. Accepts one of EAP, EB, FB.
shrinkage_correction Set TRUE to correct for shrinkage in EAP
prior_dist The type of prior distribution. Accepts one of NORMAL, UNIF.
prior_par Distributional parameters for the prior.
bound_ML Theta bound for MLE.
truncate_ML Set TRUE to truncate MLE within bound_ML
max_iter Maximum number of Newton-Raphson iterations.
crit Convergence criterion.
max_change Maximum change in ML estimates between iterations.
do_fisher Set TRUE to use Fisher's method of scoring.
A list containing final theta estimation options.
method The type of estimation. Accepts one of EAP, EB, FB.
shrinkage_correction Set TRUE to correct for shrinkage in EAP.
prior_dist The type of prior distribution. Accepts one of NORMAL, UNIF.
prior_par Distributional parameters for the prior.
bound_ML Theta bound for MLE.
truncate_ML Set TRUE to truncate MLE within bound_ML
max_iter Maximum number of Newton-Raphson iterations.
crit Convergence criterion.
max_change Maximum change in ML estimates between iterations.
do_fisher Set TRUE to use Fisher's method of scoring.
A numeric vector. Theta values to represent the continuum.
Set TRUE to generate audit trails.
# NOT RUN {
cfg1 <- createShadowTestConfig(refresh_policy = list(
method = "STIMULUS"
))
cfg2 <- createShadowTestConfig(refresh_policy = list(
method = "POSITION",
position = c(1, 5, 9)
))
# }
Run the code above in your browser using DataLab