Estimation of Optimal Size for a Holdout Set for Updating a Predictive Score

---

Documentation for package ‘OptHoldoutSize’ version 0.1.0.0

• DESCRIPTION file.
• User guides, package vignettes and other documentation.
• Package NEWS.

Help Pages

add_aspre_interactions	Add interaction terms corresponding to ASPRE model
aspre	Computes ASPRE score
aspre_emulation	Emulation-based OHS estimation for ASPRE
aspre_k2	Cost estimating function in ASPRE simulation
aspre_parametric	Parametric-based OHS estimation for ASPRE
ci_cover_a_yn	Data for example on asymptotic confidence interval for OHS.
ci_cover_cost_a_yn	Data for example on asymptotic confidence interval for min cost.
ci_cover_cost_e_yn	Data for example on empirical confidence interval for min cost.
ci_cover_e_yn	Data for example on empirical confidence interval for OHS.
ci_mincost	Confidence interval for minimum total cost, when estimated using parametric method
ci_ohs	Confidence interval for optimal holdout size, when estimated using parametric method
cov_fn	Covariance function for Gaussian process
data_example_simulation	Data for vignette showing general example
data_nextpoint_em	Data for 'next point' demonstration vignette on algorithm comparison using emulation algorithm
data_nextpoint_par	Data for 'next point' demonstration vignette on algorithm comparison using parametric algorithm
error_ohs_emulation	Measure of error for emulation-based OHS emulation
exp_imp_fn	Expected improvement
gen_base_coefs	Coefficients for imperfect risk score
gen_preds	Generate matrix of random observations
gen_resp	Generate response
grad_mincost_powerlaw	Gradient of minimum cost (power law)
grad_nstar_powerlaw	Gradient of optimal holdout size (power law)
logistic	Logistic
logit	Logit
model_predict	Make predictions
model_train	Train model (wrapper)
mu_fn	Updating function for mean.
next_n	Finds best value of n to sample next
ohs_array	Data for vignette on algorithm comparison
ohs_resample	Data for vignette on algorithm comparison
optimal_holdout_size	Estimate optimal holdout size under parametric assumptions
optimal_holdout_size_emulation	Estimate optimal holdout size under semi-parametric assumptions
oracle_pred	Generate responses
params_aspre	Parameters of reported ASPRE dataset
plot.optholdoutsize	Plot estimated cost function
plot.optholdoutsize_emul	Plot estimated cost function using emulation (semiparametric)
powerlaw	Power law function
powersolve	Fit power law curve
powersolve_general	General solver for power law curve
powersolve_se	Standard error matrix for learning curve parameters (power law)
psi_fn	Updating function for variance.
sens10	Sensitivity at theshold quantile 10%
sim_random_aspre	Simulate random dataset similar to ASPRE training data
split_data	Split data