{"id":27389476,"url":"https://github.com/johanneskopton/evpi","last_synced_at":"2025-04-13T19:15:03.196Z","repository":{"id":181266909,"uuid":"568759213","full_name":"johanneskopton/evpi","owner":"johanneskopton","description":"A fast implementation of the Expected Value of Perfect Parameter Information (EVPPI) for large Monte Carlo simulations","archived":false,"fork":false,"pushed_at":"2024-02-29T17:12:37.000Z","size":114,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-06-11T18:53:14.843Z","etag":null,"topics":["decision-analysis"],"latest_commit_sha":null,"homepage":"https://doi.org/10.5281/zenodo.10728646","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"lgpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/johanneskopton.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2022-11-21T10:55:11.000Z","updated_at":"2024-02-29T17:20:22.000Z","dependencies_parsed_at":"2024-02-29T15:47:01.489Z","dependency_job_id":null,"html_url":"https://github.com/johanneskopton/evpi","commit_stats":null,"previous_names":["johanneskopton/evpi"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/johanneskopton%2Fevpi","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/johanneskopton%2Fevpi/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/johanneskopton%2Fevpi/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/johanneskopton%2Fevpi/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/johanneskopton","download_url":"https://codeload.github.com/johanneskopton/evpi/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248766768,"owners_count":21158301,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["decision-analysis"],"created_at":"2025-04-13T19:15:02.412Z","updated_at":"2025-04-13T19:15:03.186Z","avatar_url":"https://github.com/johanneskopton.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.10728646.svg)](https://doi.org/10.5281/zenodo.10728646)\n\n\n# A fast implementation of the Expected Value of Perfect Parameter Information (EVPPI) for large Monte Carlo simulations\n\nIn this repository you can find 4 things:\n\n* a Python/Numpy implementation in [`python`](./python/README.md)\n* a C implementation in `c`\n* R bindings to the C implementation in [`r`](./r/evpi/README.md)\n* Python bindings to the C implementation using CFFI in [`python_cffi`](./python_cffi/README.md)\n\nThe _Expected Value of Perfect Parameter Information_ (EVPPI) is a concept from decision analysis (modeling decisions under uncertainty). It can be described as a measure for what a (rational) decision-maker would be willing to pay for zero uncertainty on a certain variable.\n\nIn general, the functions in this repository take in samples from a Monte Carlo model that predicts utility as a function of uncertain input parameters. Here, `x` denotes the values of the (uncertain) parameter inputs and `y` the resulting utility. More detailed documentation can be found in the respective packages.\n\nRunning the C implementation from R was found to be many times faster than existing R implementations, especially for a large number of Monte Carlo samples.\n\nDetails and limitations regarding the algorithmic approach can be found in _Brennan et al. (2007)_[^1]. There are more sophisticated approaches [^2] [^3] with advantages in some use cases, but a fast and stable implementation of this basic algorithm was considered useful for science and practice.\n\n## References\n[^1]: Brennan, A., Kharroubi, S., O’Hagan, A., \u0026 Chilcott, J. (2007). Calculating Partial Expected Value of Perfect Information via Monte Carlo Sampling Algorithms. Medical Decision Making, 27(4), 448–470. https://doi.org/10.1177/0272989X07302555\n\n[^2]: Strong, M., \u0026 Oakley, J. E. (2013). An Efficient Method for Computing Single-Parameter Partial Expected Value of Perfect Information. https://journals.sagepub.com/doi/10.1177/0272989X12465123\n\n[^3]: Strong, M., Oakley, J. E., \u0026 Brennan, A. (2014). Estimating Multiparameter Partial Expected Value of Perfect Information from a Probabilistic Sensitivity Analysis Sample: A Nonparametric Regression Approach. Medical Decision Making, 34(3), 311–326. https://doi.org/10.1177/0272989X13505910\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjohanneskopton%2Fevpi","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjohanneskopton%2Fevpi","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjohanneskopton%2Fevpi/lists"}