priorsense

priorsense: an R package for prior diagnostics and sensitivity

https://github.com/n-kall/priorsense

Science Score: 57.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
✓
DOI references
Found 6 DOI reference(s) in README
○
Academic publication links
○
Committers with academic emails
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (14.1%) to scientific vocabulary

Keywords

bayes bayesian bayesian-data-analysis bayesian-methods prior-distribution r r-package sensitivity-analysis stan

Last synced: 6 months ago · JSON representation ·

Repository

priorsense: an R package for prior diagnostics and sensitivity

Basic Info

Host: GitHub
Owner: n-kall
License: gpl-3.0
Language: R
Default Branch: main
Homepage: https://n-kall.github.io/priorsense/
Size: 10.6 MB

Statistics

Stars: 64
Watchers: 5
Forks: 9
Open Issues: 4
Releases: 0

Topics

bayes bayesian bayesian-data-analysis bayesian-methods prior-distribution r r-package sensitivity-analysis stan

Created over 4 years ago · Last pushed 6 months ago

Metadata Files

Readme Changelog Contributing License Citation Codemeta

priorsense

Overview

priorsense provides tools for prior diagnostics and sensitivity analysis.

It currently includes functions for performing power-scaling sensitivity analysis on Stan models. This is a way to check how sensitive a posterior is to perturbations of the prior and likelihood and diagnose the cause of sensitivity. For efficient computation, power-scaling sensitivity analysis relies on Pareto smoothed importance sampling (Vehtari et al., 2024) and importance weighted moment matching (Paananen et al., 2021).

Power-scaling sensitivity analysis and priorsense are described in Kallioinen et al. (2023).

Installation

Download the stable version from CRAN with:

r install.packages("priorsense")

Download the development version from GitHub with:

``` r

install.packages("remotes")

remotes::install_github("n-kall/priorsense", ref = "development") ```

Usage

priorsense works with models created with rstan, cmdstanr, brms, R2jags, or with draws objects from the posterior package.

Example

Consider a simple univariate model with unknown mu and sigma fit to some data y (available viaexample_powerscale_model("univariate_normal")):

stan data { int<lower=1> N; array[N] real y; } parameters { real mu; real<lower=0> sigma; } model { // priors target += normal_lpdf(mu | 0, 1); target += normal_lpdf(sigma | 0, 2.5); // likelihood target += normal_lpdf(y | mu, sigma); } generated quantities { vector[N] log_lik; real lprior; // log likelihood for (n in 1:N) log_lik[n] = normal_lpdf(y[n] | mu, sigma); // joint log prior lprior = normal_lpdf(mu | 0, 1) + normal_lpdf(sigma | 0, 2.5);

We first fit the model using Stan:

``` r library(priorsense)

normalmodel <- examplepowerscalemodel("univariatenormal")

fit <- rstan::stan( modelcode = normalmodel$modelcode, data = normalmodel$data, refresh = FALSE, seed = 123 ) ```

Once fit, sensitivity can be checked as follows:

r powerscale_sensitivity(fit)

Sensitivity based on cjs_dist
Prior selection: all priors
Likelihood selection: all data

 variable prior likelihood                     diagnosis
       mu  0.43       0.64 potential prior-data conflict
    sigma  0.36       0.67 potential prior-data conflict

To visually inspect changes to the posterior, use one of the diagnostic plot functions. Estimates with high Pareto-k values may be inaccurate and are indicated.

r powerscale_plot_dens(fit)

r powerscale_plot_ecdf(fit)

r powerscale_plot_quantities(fit)

In some cases, setting moment_match = TRUE will improve the unreliable estimates at the cost of some further computation. This requires the iwmm package.

Contributing

Contributions are welcome! If you find an bug or have an idea for a feature, open an issue. If you are able to fix an issue, fork the repository and make a pull request to the development branch.

References

Noa Kallioinen, Topi Paananen, Paul-Christian Bürkner, Aki Vehtari (2023). Detecting and diagnosing prior and likelihood sensitivity with power-scaling. Statistics and Computing. 34, 57. https://doi.org/10.1007/s11222-023-10366-5

Topi Paananen, Juho Piironen, Paul-Christian Bürkner, Aki Vehtari (2021). Implicitly adaptive importance sampling. Statistics and Computing 31, 16. https://doi.org/10.1007/s11222-020-09982-2

Aki Vehtari, Daniel Simpson, Andrew Gelman, Yuling Yao, Jonah Gabry (2024). Pareto smoothed importance sampling. Journal of Machine Learning Research. 25, 72. https://jmlr.org/papers/v25/19-556.html

Owner

Login: n-kall
Kind: user

Repositories: 9
Profile: https://github.com/n-kall

Citation (CITATION.cff)

cff-version: "1.2.0"
message: If you use this software, please cite our article in Statistics and Computing.
preferred-citation:
  type: article
  authors:
  - family-names: Kallioinen
    given-names: Noa
    orcid: "https://orcid.org/0000-0003-1586-8382"
  - family-names: Paananen
    given-names: Topi
    orcid: "https://orcid.org/0000-0002-6542-407X"
  - family-names: Bürkner
    given-names: Paul-Christian
    orcid: "https://orcid.org/0000-0001-5765-8995"
  - family-names: Vehtari
    given-names: Aki
    orcid: "https://orcid.org/0000-0003-2164-9469"
  year: 2023
  doi: 10.1007/s11222-023-10366-5
  pages: 57
  journal: Statistics and Computing
  publisher:
    name: Springer Nature
  volume: 34
  title: "Detecting and diagnosing prior and likelihood sensitivity with power-scaling"
  url: "https://link.springer.com/article/10.1007/s11222-023-10366-5"

CodeMeta (codemeta.json)

{
  "@context": "https://doi.org/10.5063/schema/codemeta-2.0",
  "@type": "SoftwareSourceCode",
  "identifier": "priorsense",
  "description": "Provides functions for prior and likelihood sensitivity analysis in Bayesian models. Currently it implements methods to determine the sensitivity of the posterior to power-scaling perturbations of the prior and likelihood.",
  "name": "priorsense: Prior Diagnostics and Sensitivity Analysis",
  "relatedLink": [
    "https://n-kall.github.io/priorsense/",
    "https://CRAN.R-project.org/package=priorsense"
  ],
  "codeRepository": "https://github.com/n-kall/priorsense",
  "issueTracker": "https://github.com/n-kall/priorsense/issues",
  "license": "https://spdx.org/licenses/GPL-3.0",
  "version": "1.1.0",
  "programmingLanguage": {
    "@type": "ComputerLanguage",
    "name": "R",
    "url": "https://r-project.org"
  },
  "runtimePlatform": "R version 4.4.3 (2025-02-28)",
  "provider": {
    "@id": "https://cran.r-project.org",
    "@type": "Organization",
    "name": "Comprehensive R Archive Network (CRAN)",
    "url": "https://cran.r-project.org"
  },
  "author": [
    {
      "@type": "Person",
      "givenName": "Noa",
      "familyName": "Kallioinen",
      "email": "noa.kallioinen@aalto.fi"
    },
    {
      "@type": "Person",
      "givenName": "Topi",
      "familyName": "Paananen"
    },
    {
      "@type": "Person",
      "givenName": "Paul-Christian",
      "familyName": "Brkner"
    },
    {
      "@type": "Person",
      "givenName": "Aki",
      "familyName": "Vehtari"
    }
  ],
  "contributor": [
    {
      "@type": "Person",
      "givenName": "Frank",
      "familyName": "Weber"
    }
  ],
  "copyrightHolder": [
    {
      "@type": "Person",
      "givenName": "Noa",
      "familyName": "Kallioinen",
      "email": "noa.kallioinen@aalto.fi"
    }
  ],
  "maintainer": [
    {
      "@type": "Person",
      "givenName": "Noa",
      "familyName": "Kallioinen",
      "email": "noa.kallioinen@aalto.fi"
    }
  ],
  "softwareSuggestions": [
    {
      "@type": "SoftwareApplication",
      "identifier": "R2jags",
      "name": "R2jags",
      "version": ">= 0.8",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=R2jags"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "bayesplot",
      "name": "bayesplot",
      "version": ">= 1.11.1",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=bayesplot"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "brms",
      "name": "brms",
      "version": ">= 2.22.0",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=brms"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "cmdstanr",
      "name": "cmdstanr",
      "version": ">= 0.8.1"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "iwmm",
      "name": "iwmm",
      "version": ">= 0.0.1"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "quarto",
      "name": "quarto",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=quarto"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "philentropy",
      "name": "philentropy",
      "version": ">= 0.8.0",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=philentropy"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "rstan",
      "name": "rstan",
      "version": ">= 2.32.6",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=rstan"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "testthat",
      "name": "testthat",
      "version": ">= 3.0.0",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=testthat"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "transport",
      "name": "transport",
      "version": ">= 0.15",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=transport"
    }
  ],
  "softwareRequirements": {
    "1": {
      "@type": "SoftwareApplication",
      "identifier": "checkmate",
      "name": "checkmate",
      "version": ">= 2.3.1",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=checkmate"
    },
    "2": {
      "@type": "SoftwareApplication",
      "identifier": "ggdist",
      "name": "ggdist",
      "version": ">= 3.3.2",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=ggdist"
    },
    "3": {
      "@type": "SoftwareApplication",
      "identifier": "ggh4x",
      "name": "ggh4x",
      "version": ">= 0.2.5",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=ggh4x"
    },
    "4": {
      "@type": "SoftwareApplication",
      "identifier": "ggplot2",
      "name": "ggplot2",
      "version": ">= 3.5.1",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=ggplot2"
    },
    "5": {
      "@type": "SoftwareApplication",
      "identifier": "grDevices",
      "name": "grDevices",
      "version": ">= 3.6.2"
    },
    "6": {
      "@type": "SoftwareApplication",
      "identifier": "matrixStats",
      "name": "matrixStats",
      "version": ">= 1.3.0",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=matrixStats"
    },
    "7": {
      "@type": "SoftwareApplication",
      "identifier": "posterior",
      "name": "posterior",
      "version": ">= 1.6.0",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=posterior"
    },
    "8": {
      "@type": "SoftwareApplication",
      "identifier": "rlang",
      "name": "rlang",
      "version": ">= 1.1.4",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=rlang"
    },
    "9": {
      "@type": "SoftwareApplication",
      "identifier": "stats",
      "name": "stats"
    },
    "10": {
      "@type": "SoftwareApplication",
      "identifier": "tibble",
      "name": "tibble",
      "version": ">= 3.2.1",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=tibble"
    },
    "11": {
      "@type": "SoftwareApplication",
      "identifier": "utils",
      "name": "utils"
    },
    "12": {
      "@type": "SoftwareApplication",
      "identifier": "R",
      "name": "R",
      "version": ">= 3.6.0"
    },
    "SystemRequirements": null
  },
  "fileSize": "2273.618KB",
  "citation": [
    {
      "@type": "ScholarlyArticle",
      "datePublished": "2023",
      "author": [
        {
          "@type": "Person",
          "givenName": "Noa",
          "familyName": "Kallioinen"
        },
        {
          "@type": "Person",
          "givenName": "Topi",
          "familyName": "Paananen"
        },
        {
          "@type": "Person",
          "givenName": "Paul-Christian",
          "familyName": "Brkner"
        },
        {
          "@type": "Person",
          "givenName": "Aki",
          "familyName": "Vehtari"
        }
      ],
      "name": "Detecting and diagnosing prior and likelihood sensitivity with power-scaling",
      "identifier": "10.1007/s11222-023-10366-5",
      "@id": "https://doi.org/10.1007/s11222-023-10366-5",
      "sameAs": "https://doi.org/10.1007/s11222-023-10366-5",
      "isPartOf": {
        "@type": "PublicationIssue",
        "datePublished": "2023",
        "isPartOf": {
          "@type": [
            "PublicationVolume",
            "Periodical"
          ],
          "volumeNumber": "34",
          "name": "Statistics and Computing"
        }
      }
    },
    {
      "@type": "ScholarlyArticle",
      "datePublished": "2024",
      "author": [
        {
          "@type": "Person",
          "givenName": "Aki",
          "familyName": "Vehtari"
        },
        {
          "@type": "Person",
          "givenName": "Daniel",
          "familyName": "Simpson"
        },
        {
          "@type": "Person",
          "givenName": "Andrew",
          "familyName": "Gelman"
        },
        {
          "@type": "Person",
          "givenName": "Yuling",
          "familyName": "Yao"
        },
        {
          "@type": "Person",
          "givenName": "Jonah",
          "familyName": "Gabry"
        }
      ],
      "name": "Pareto smoothed importance sampling",
      "isPartOf": {
        "@type": "PublicationIssue",
        "datePublished": "2024",
        "isPartOf": {
          "@type": [
            "PublicationVolume",
            "Periodical"
          ],
          "volumeNumber": "25",
          "name": "Journal of Machine Learning Research"
        }
      }
    },
    {
      "@type": "ScholarlyArticle",
      "datePublished": "2021",
      "author": [
        {
          "@type": "Person",
          "givenName": "Topi",
          "familyName": "Paananen"
        },
        {
          "@type": "Person",
          "givenName": "Juho",
          "familyName": "Piironen"
        },
        {
          "@type": "Person",
          "givenName": "Paul-Christian",
          "familyName": "Brkner"
        },
        {
          "@type": "Person",
          "givenName": "Aki",
          "familyName": "Vehtari"
        }
      ],
      "name": "Implicitly adaptive importance sampling",
      "identifier": "10.1007/s11222-020-09982-2",
      "pagination": "1--19",
      "@id": "https://doi.org/10.1007/s11222-020-09982-2",
      "sameAs": "https://doi.org/10.1007/s11222-020-09982-2",
      "isPartOf": {
        "@type": "PublicationIssue",
        "datePublished": "2021",
        "isPartOf": {
          "@type": [
            "PublicationVolume",
            "Periodical"
          ],
          "volumeNumber": "31",
          "name": "Statistics and Computing"
        }
      }
    }
  ],
  "releaseNotes": "https://github.com/n-kall/priorsense/blob/master/NEWS.md",
  "readme": "https://github.com/n-kall/priorsense/blob/main/README.md",
  "contIntegration": "https://github.com/n-kall/priorsense/actions",
  "developmentStatus": "https://lifecycle.r-lib.org/articles/stages.html#stable",
  "keywords": [
    "bayesian-data-analysis",
    "bayesian-methods",
    "prior-distribution",
    "r-package",
    "sensitivity-analysis",
    "stan",
    "bayesian",
    "r",
    "bayes"
  ]
}

GitHub Events

Total

Issues event: 22
Watch event: 8
Delete event: 8
Issue comment event: 16
Push event: 123
Pull request event: 46
Fork event: 4
Create event: 9

Last Year

Issues event: 22
Watch event: 8
Delete event: 8
Issue comment event: 16
Push event: 123
Pull request event: 46
Fork event: 4
Create event: 9

Committers

Last synced: 9 months ago

All Time

Total Commits: 544
Total Committers: 7
Avg Commits per committer: 77.714
Development Distribution Score (DDS): 0.283

Past Year

Commits: 149
Committers: 3
Avg Commits per committer: 49.667
Development Distribution Score (DDS): 0.242

Top Committers

Name	Email	Commits
n-kall	n**l@g**m	390
n-kall	3****l	117
fweber144	f**4@p**m	14
Rantaharju Jarno	j**u@a**i	12
Andrew Johnson	a**n@a**m	7
Sam A.S. Welch	1****A	3
Andrey Akinshin	a**n@g**m	1

Committer Domains (Top 20 + Academic)

arjohnsonau.com: 1 aalto.fi: 1 github.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 34
Total pull requests: 86
Average time to close issues: 7 months
Average time to close pull requests: 10 days
Total issue authors: 14
Total pull request authors: 8
Average comments per issue: 1.71
Average comments per pull request: 0.09
Merged pull requests: 72
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 12
Pull requests: 52
Average time to close issues: about 1 month
Average time to close pull requests: 2 days
Issue authors: 3
Pull request authors: 3
Average comments per issue: 1.17
Average comments per pull request: 0.0
Merged pull requests: 41
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

n-kall (14)
avehtari (4)
rantahar (2)
jflournoy (2)
paul-buerkner (2)
maxbiostat (1)
dirknbr (1)
fweber144 (1)
TeemuSailynoja (1)
Sandhu-SS (1)
AndHofma (1)
bcs-alexander (1)
lcgodoy (1)
fraupflaume (1)
cmgoold (1)

Pull Request Authors

n-kall (99)
samawelch (6)
rantahar (3)
AndreyAkinshin (2)
GiorgioMB (2)
andrjohns (1)
harris-yh-wong (1)
fweber144 (1)

Top Labels

Issue Labels

ro-hackathon-2025 (7) good first issue (5) help wanted (4) documentation (1) bug (1) enhancement (1)

Pull Request Labels

Packages

Total packages: 1
Total downloads:
- cran 1,429 last-month

Total dependent packages: 0
Total dependent repositories: 0
Total versions: 7
Total maintainers: 1

cran.r-project.org: priorsense

Prior Diagnostics and Sensitivity Analysis

Homepage: https://github.com/n-kall/priorsense
Documentation: http://cran.r-project.org/web/packages/priorsense/priorsense.pdf
License: GPL (≥ 3)
Latest release: 1.1.1
published 6 months ago

Versions: 7
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 1,429 Last month

Rankings

Dependent packages count: 28.7%

Dependent repos count: 35.4%

Average: 50.1%

Downloads: 86.3%

Maintainers (1)

noa.kallioinen@aalto.fi

Last synced: 6 months ago

Dependencies

DESCRIPTION cran

R >= 3.6.0 depends
cetcolor * imports
checkmate * imports
ggplot2 * imports
loo * imports
matrixStats * imports
methods * imports
philentropy * imports
posterior * imports
stats * imports
tibble * imports
transport * imports
utils * imports
brms * suggests
knitr * suggests
rmarkdown * suggests
rstan * suggests
testthat >= 3.0.0 suggests

.github/workflows/R-CMD-check.yaml actions

actions/checkout v2 composite
n1hility/cancel-previous-runs v2 composite
r-lib/actions/check-r-package v2 composite
r-lib/actions/setup-pandoc v2 composite
r-lib/actions/setup-r v2 composite
r-lib/actions/setup-r-dependencies v2 composite

.github/workflows/render-rmarkdown.yaml actions

actions/checkout v2 composite
n1hility/cancel-previous-runs v2 composite
r-lib/actions/setup-pandoc v2 composite
r-lib/actions/setup-r v2 composite
r-lib/actions/setup-r-dependencies v2 composite