https://github.com/sircornflake/bms
Tools to perform model selection alongside estimation under Linear, Logistic, Negative binomial, Quantile, and Skew-Normal regression. Under the spike-and-slab method, a probability for each possible model is estimated with the posterior mean, credibility interval, and standard deviation of coefficients and parameters under the most probable model.
https://github.com/sircornflake/bms
bayesian-data-analysis bayesian-inference bayesian-methods bayesian-statistics model-selection modelselection variable-selection
Last synced: about 8 hours ago
JSON representation
Tools to perform model selection alongside estimation under Linear, Logistic, Negative binomial, Quantile, and Skew-Normal regression. Under the spike-and-slab method, a probability for each possible model is estimated with the posterior mean, credibility interval, and standard deviation of coefficients and parameters under the most probable model.
- Host: GitHub
- URL: https://github.com/sircornflake/bms
- Owner: SirCornflake
- Created: 2024-04-02T23:55:24.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2025-04-05T22:29:19.000Z (over 1 year ago)
- Last Synced: 2026-06-30T05:12:23.792Z (14 days ago)
- Topics: bayesian-data-analysis, bayesian-inference, bayesian-methods, bayesian-statistics, model-selection, modelselection, variable-selection
- Language: R
- Homepage: https://cran.r-project.org/web/packages/abms/index.html
- Size: 304 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# BMS
For R software.
These files contain the necessary functions to perform a Bayesian model selection methodology based on the spike-and-slab strategy and an augmentation technique for Linear, Logistic, Negative Binomial, Quantile, and Skew Normal Regression. The model considers a response vector "y" of size "n" and "p" predictors to perform coefficient estimation and asses which ones are relevant to explain the response distribution. These files are the extra examples mentioned in the R package "abms", which is contained in CRAN.
1. "function.R": A R script that contains all the necessary functions to perform estimation and model selection in Linear, Logistic, Negative-Binomial, Quantile, and Skew-Normal regression. This functions are in the R package "abms".
2. "Model Ilustrations.R": A R script that can be used to illustrate all five regression models. “summary_gibbs” function provides the posterior mean of parameters and quantile 2.5% and 97.5%, alongside the explored models with their respective proportion of times that was selected.
3. "Simulation Study.R": A R script where the simulation study's tables and figures of the manuscript and supplementary material can be reproduced
4. "Application Code.R": A R script where the application results can be replicated For the Application reproducibility. It is held in the "Application" folder.
5. "ens.csv": A ".csv" file that contains the data set used in the "Application Code.R" file. It is held in the "Application" folder.
6. “ens_description.pdf”: Data dictionary for the "ens" data-set. It is held in the "Application" folder.