Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/nignatiadis/empirical-bayes-data-fission-comment
https://github.com/nignatiadis/empirical-bayes-data-fission-comment
Last synced: 26 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/nignatiadis/empirical-bayes-data-fission-comment
- Owner: nignatiadis
- License: mit
- Created: 2024-08-22T21:31:41.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2024-08-22T23:31:30.000Z (5 months ago)
- Last Synced: 2024-08-23T00:59:16.628Z (5 months ago)
- Language: R
- Size: 4.88 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# empirical-bayes-data-fission-comment
The main scripts are the following:
* `gaussian_aurora.R`: Simulations for EB estimation with a normal likelihood. Running this script generates two files:
* "double_gaussian_plot.png" which is panel (a) of Figure 1
* "double_gaussian_MSE.csv", which contains the data for the column "Gaussian MSE" of Table 1* `poisson_aurora.R`: Simulations for EB estimation with a Poisson likelihood. Running this script generates two files:
* "double_poisson_plot.png" which is panel (b) of Figure 1
* "double_poisson_MSE.csv", which contains the data for the column "Poisson MSE" of Table 1## Further instructions
Running the above two scripts presupposes a working installation of R and several packages. The following file
* `R_session_info.txt`
records the session information about the version of R used as well as of all required packages.
For the implementation of the nonparametric maximum likelihood estimator (NPMLE), we used the CRAN R package [REBayes](https://cran.r-project.org/web/packages/REBayes/index.html).
REBayes requires a working installation of the commercial optimization solver [Mosek](https://www.mosek.com/) (we used Mosek version 10.1). Mosek provides [free licenses for academic use](https://www.mosek.com/products/academic-licenses/).