# --------------------------------------------
# CITATION file created with {cffr} R package
# See also: https://docs.ropensci.org/cffr/
# --------------------------------------------
 
cff-version: 1.2.0
message: 'To cite package "cramR" in publications use:'
type: software
license: GPL-3.0-only
title: 'cramR: Cram Method for Efficient Simultaneous Learning and Evaluation'
version: 0.1.0
identifiers:
- type: doi
  value: 10.32614/CRAN.package.cramR
abstract: Performs the Cram method, a general and efficient approach to simultaneous
  learning and evaluation using a generic machine learning algorithm. In a single
  pass of batched data, the proposed method repeatedly trains a machine learning algorithm
  and tests its empirical performance. Because it utilizes the entire sample for both
  learning and evaluation, cramming is significantly more data-efficient than sample-splitting.
  Unlike cross-validation, Cram evaluates the final learned model directly, providing
  sharper inference aligned with real-world deployment. The method naturally applies
  to both policy learning and contextual bandits, where decisions are based on individual
  features to maximize outcomes. The package includes cram_policy() for learning and
  evaluating individualized binary treatment rules, cram_ml() to train and assess
  the population-level performance of machine learning models, and cram_bandit() for
  on-policy evaluation of contextual bandit algorithms. For all three functions, the
  package provides estimates of the average outcome that would result if the model
  were deployed, along with standard errors and confidence intervals for these estimates.
  Details of the method are described in Jia, Imai, and Li (2024) <https://www.hbs.edu/ris/Publication%20Files/2403.07031v1_a83462e0-145b-4675-99d5-9754aa65d786.pdf>
  and Jia et al. (2025) <https://doi.org/10.48550/arXiv.2403.07031>.
authors:
- family-names: Vandecasteele
  given-names: Yanis
  email: yanisvdc.ensae@gmail.com
preferred-citation:
  type: manual
  title: 'cramR: The Cram Method for Efficient Simultaneous Learning and Evaluation'
  authors:
  - family-names: Vandecasteele
    given-names: Yanis
    email: yanisvdc.ensae@gmail.com
  - family-names: Li
    given-names: Michael Lingzhi
  - family-names: Imai
    given-names: Kosuke
  - family-names: Jia
    given-names: Zeyang
  - family-names: Wang
    given-names: Longlin
  year: '2025'
  notes: Package developed and maintained by Yanis Vandecasteele.
  url: https://github.com/yanisvdc/cramR
repository: https://yanisvdc.r-universe.dev
repository-code: https://github.com/yanisvdc/cramR
commit: b6d7444fd9f0ea7eabec603642b62818caf8e724
url: https://yanisvdc.github.io/cramR/
date-released: '2025-05-11'
contact:
- family-names: Vandecasteele
  given-names: Yanis
  email: yanisvdc.ensae@gmail.com
references:
- type: report
  title: The Cram Method for Efficient Simultaneous Learning and Evaluation
  authors:
  - family-names: Jia
    given-names: Zeyang
  - family-names: Imai
    given-names: Kosuke
  - family-names: Li
    given-names: Michael Lingzhi
  institution:
    name: Harvard Business School
  year: '2024'
  url: https://www.hbs.edu/ris/Publication%20Files/2403.07031v1_a83462e0-145b-4675-99d5-9754aa65d786.pdf
  notes: Accessed April 2025
- type: generic
  title: Cramming Contextual Bandits for On-policy Statistical Evaluation
  authors:
  - family-names: Jia
    given-names: Zeyang
  - family-names: Imai
    given-names: Kosuke
  - family-names: Li
    given-names: Michael Lingzhi
  year: '2025'
  url: https://arxiv.org/abs/2403.07031