OptHoldoutSize0.1.0.1 package

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

add_aspre_interactions

Add interaction terms corresponding to ASPRE model

aspre_k2

Cost estimating function in ASPRE simulation

aspre

Computes ASPRE score

ci_mincost

Confidence interval for minimum total cost, when estimated using param...

ci_ohs

Confidence interval for optimal holdout size, when estimated using par...

cov_fn

Covariance function for Gaussian process

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

optimal_holdout_size_emulation

Estimate optimal holdout size under semi-parametric assumptions

optimal_holdout_size

Estimate optimal holdout size under parametric assumptions

oracle_pred

Generate responses

plot.optholdoutsize_emul

Plot estimated cost function using emulation (semiparametric)

plot.optholdoutsize

Plot estimated cost function

powerlaw

Power law function

powersolve_general

General solver for power law curve

powersolve_se

Standard error matrix for learning curve parameters (power law)

powersolve

Fit power law curve

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

Predictive scores must be updated with care, because actions taken on the basis of existing risk scores causes bias in risk estimates from the updated score. A holdout set is a straightforward way to manage this problem: a proportion of the population is 'held-out' from computation of the previous risk score. This package provides tools to estimate a size for this holdout set and associated errors. Comprehensive vignettes are included. Please see: Haidar-Wehbe S, Emerson SR, Aslett LJM, Liley J (2022) <doi:10.48550/arXiv.2202.06374> (to appear in Annals of Applied Statistics) for details of methods.

  • Maintainer: James Liley
  • License: GPL (>= 3)
  • Last published: 2025-04-09