Estimate epidemiological delay distributions with `brms`

Summary

Understanding and accurately estimating epidemiological delay distributions is important for public health policy. These estimates influence epidemic situational awareness, control strategies, and resource allocation. This package provides methods to address the key challenges in estimating these distributions, including truncation, interval censoring, and dynamical biases, following Park et al. (2024) doi:10.1101/2024.01.12.24301247 and Charniga et al. (2024) doi:10.1371/journal.pcbi.1012520. These issues are frequently overlooked, resulting in biased conclusions. Built on top of ‘brms’, it allows for flexible modelling including time-varying and spatial effects and partially pooled estimates of demographic characteristics.

Quickstart

To learn more about epidist we recommend reading the vignettes in this order:

To get started, fitting a delay distribution to individual level data.
For the models we support and the biases each one corrects, the model guide.
For a worked example on real data, delays from symptom onset to positive test in an Ebola outbreak.
For fitting to published estimates, and adjusting them for how each study was estimated, the meta model.
For faster fits on larger data, approximate Bayesian inference.
For questions that come up in use, the FAQ.

Installation

Installing the package

You can install the latest released version from CRAN using the standard install.packages function:

install.packages("epidist")

Alternatively, you can install the latest release from our r-universe repository:

install.packages("epidist", repos = "https://epinowcast.r-universe.dev")

To install the development version from GitHub (warning! this version may contain breaking changes and/or bugs), use the pak package:

pak::pak("epinowcast/epidist")

Similarly, you can install historical versions by specifying the release tag (e.g., v0.4.0):

pak::pak("epinowcast/epidist@v0.4.0")

Note: You can also use the above approach to install a specific commit if needed, for example, if you want to try out a specific unreleased feature, but not the absolute latest developmental version.

Installing CmdStan (optional)

By default epidist uses the rstan package for fitting models. If you wish to use the cmdstanr package instead, you will need to install CmdStan, which also entails having a suitable C++ toolchain setup. We recommend using the cmdstanr package to manage CmdStan. The Stan team provides instructions in the Getting started with cmdstanr vignette, with other details and support at the package site, but the brief version is:

# `cmdstanr` is not a dependency of `epidist`, so install it yourself
install.packages(
  "cmdstanr",
  repos = c("https://stan-dev.r-universe.dev", getOption("repos"))
)

# once `cmdstanr` is installed
cmdstanr::install_cmdstan()

Note: You can speed up CmdStan installation using the cores argument. If you are installing a particular version of epidist, you may also need to install a past version of CmdStan, which you can do with the version argument.

Resources

Organisation Website

Our organisation website includes links to other resources, guest posts, and seminar schedule for both upcoming and past recordings.

Community Forum

Our community forum has areas for question and answer and considering new methods and tools, among others. If you are generally interested in real-time analysis of infectious disease, you may find this useful even if do not use epidist.

Contributing

We welcome contributions and new contributors! We particularly appreciate help on identifying and identified issues. Please check and add to the issues, and/or add a pull request and see our contributing guide for more information.

How to make a bug report or feature request

Please briefly describe your problem and what output you expect in an issue.

If you have a question, please don’t open an issue. Instead, ask on our forum.

See our contributing guide for more information.

Code of Conduct

Please note that the epidist project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.

Citation

If you use epidist in your work, please consider citing it using citation("epidist").

Package citation information

citation("epidist")
To cite package 'epidist' in publications use:

  Howes A, Park S, Abbott S (2026). _epidist: Estimate Epidemiological
  Delay Distributions with 'brms'_. doi:10.5281/zenodo.14213017
  <https://doi.org/10.5281/zenodo.14213017>.

A BibTeX entry for LaTeX users is

  @Manual{,
    title = {epidist: Estimate Epidemiological Delay Distributions with 'brms'},
    author = {Adam Howes and Sang Woo Park and Sam Abbott},
    year = {2026},
    doi = {10.5281/zenodo.14213017},
  }

If using our methodology, or the methodology on which ours is based, please cite the relevant papers. This may include:

Estimating epidemiological delay distributions for infectious diseases by Park et al. (2024) – if using the latent model
Best practices for estimating and reporting epidemiological delay distributions of infectious diseases using public health surveillance and healthcare data by Charniga et al. (2024)

If using the marginal model, please also cite the primarycensored package using citation("primarycensored").

Contributors

All contributions to this project are gratefully acknowledged using the allcontributors package following the allcontributors specification. Contributions of any kind are welcome!

Estimate epidemiological delay distributions with brms