Freedom251 › Statistical Analysis Software
R-fitODBOD
What R-fitODBOD is
R-fitODBOD is a free R package for modeling binomial outcome data with alternate binomial and binomial mixture distributions. It lists six alternate binomial distributions and eight mixture distributions, with the mixture family intended for overdispersed binomial outcomes. The BODextract function prepares raw outcomes in the frequency format used by the examples. Fitting functions can provide expected frequencies, chi-squared statistics, p-values, and degrees of freedom for evaluating fit. Documentation covers maximum likelihood and method of moments for estimating parameters. For model selection, it recommends comparing p-values, negative log likelihood, AIC, observed-versus-expected frequency differences, and variance differences. Installation instructions are provided for GitHub and CRAN, and the package is GPL-2 licensed. The project also offers fitODBODRshiny, a Shiny application for fitting selected outcome data with these distribution families. Its walkthrough uses alcohol-consumption data from 399 respondents in the Netherlands in 1983. Later example steps require frequency-table input, and the beta-binomial example uses mle2 from the bbmle package. Bug reports can be submitted through GitHub issues.
Who it suits
It suits R users analyzing binomial outcomes, including overdispersed data, who need multiple distribution families and documented fit criteria. Users should be prepared to supply frequency-table data for later workflow steps.
What it does well
- Free package with GitHub and CRAN installation
- Includes six alternate distributions
- Includes eight mixture distributions
- Reports several goodness-of-fit measures
- Offers a Shiny application
What to know first
- Later workflow steps require frequency-table data
- Beta-binomial example depends on bbmle
- Model choice requires comparing multiple criteria
- Bug support uses GitHub issues
Verdict
R-fitODBOD provides a focused set of binomial and mixture models with several estimation and comparison measures. Its frequency-table requirement and package dependency are important when planning an analysis workflow.
Facts from R-fitODBOD's own pages
- Data preparation
- The BODextract function can prepare raw binomial outcome data in the frequency format used in the examples. · amalan-constat.github.io, 12 Oct 2026
- Dependencies
- The beta-binomial example uses mle2 from the bbmle package for maximum-likelihood estimation. · amalan-constat.github.io, 12 Oct 2026
- Distribution families
- The package lists six alternate binomial distributions and eight binomial mixture distributions. · amalan-constat.github.io, 12 Oct 2026
- Estimation
- The package documentation describes maximum likelihood and method of moments approaches for estimating distribution parameters. · amalan-constat.github.io, 12 Oct 2026
- Example data
- The site demonstrates the workflow with alcohol consumption data from 399 respondents in the Netherlands in 1983. · amalan-constat.github.io, 12 Oct 2026
- Example dataset
- The modeling example uses alcohol-consumption data from 399 respondents in the Netherlands in 1983. · amalan-constat.github.io, 12 Oct 2026
- Free plan
- Yes · amalan-constat.github.io, 23 Sept 2026
- Input format
- The modeling walkthrough says its later steps can be applied when the dataset is in frequency-table form. · amalan-constat.github.io, 12 Oct 2026
- Installation
- The maker’s site gives installation instructions for both GitHub and CRAN. · amalan-constat.github.io, 12 Oct 2026
- License
- The package is listed under the GPL-2 license. · amalan-constat.github.io, 12 Oct 2026
- Maintainers
- The project page names Amalan Mahendran as author and maintainer and Pushpakanthie Wijekoon as author and contributor. · amalan-constat.github.io, 12 Oct 2026
- Model fitting
- Fitting functions can report expected frequencies, chi-squared statistics, p-values, and degrees of freedom for assessing fit. · amalan-constat.github.io, 12 Oct 2026
- Modeling criteria
- Its example compares candidate distributions using p-values, negative log-likelihood, AIC, observed and expected frequency differences, and variance differences. · amalan-constat.github.io, 12 Oct 2026
- Model selection
- The documentation recommends comparing p-values, negative log likelihood, AIC, frequency differences, and variance differences when selecting a fit. · amalan-constat.github.io, 12 Oct 2026
- Notable limit
- The example says steps 2 through 5 can be applied only when the dataset is in frequency-table form. · amalan-constat.github.io, 12 Oct 2026
- Overdispersion
- The package describes binomial mixture distributions as useful for fitting overdispersed binomial outcome data. · amalan-constat.github.io, 12 Oct 2026
- Purpose
- fitODBOD models binomial outcome data using binomial mixture and alternate binomial distributions. · amalan-constat.github.io, 12 Oct 2026
- R Shiny application
- The maker says fitODBODRshiny is available to fit selected binomial outcome data using binomial mixture and alternate binomial distributions. · amalan-constat.github.io, 12 Oct 2026
- Scripting support
- Yes · amalan-constat.github.io, 23 Sept 2026
- Support
- The maker links to a GitHub issues page for reporting bugs. · amalan-constat.github.io, 12 Oct 2026
Where R-fitODBOD stands on Freedom251
- Statistical Analysis Software#87 of 106