# easystats/performance

:muscle: Models' quality and performance metrics (R2, ICC, LOO, AIC, BF, ...)

Repository: https://github.com/easystats/performance
Canonical: https://ross.abutalabs.com/products/performance
Homepage: https://easystats.github.io/performance/
Language: R
License: GPL-3.0
License Family: copyleft
Topics: r2, aic, performance, models, loo, r, easystats, mixed-models, statistics, hacktoberfest, machine-learning
Last push: 2026-08-26T07:57:01+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 78, longevity 100
- inputs: {"age_days": 2761, "days_push": 7, "days_rel": 64, "gap_med": 56, "n_releases_24m": 10}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1151, forks 108 (observed 2026-08-28T04:03:46.685905+00:00)

## What it is
An R package from the easystats ecosystem that computes indices of model quality and goodness of fit, such as R-squared, RMSE, ICC, AIC, and LOO. It also provides checks for overdispersion, zero-inflation, convergence, and singularity in (mixed) regression models.

## Use cases
- compute r-squared for a regression model in R
- calculate intraclass correlation coefficient for a mixed model
- compare model fit with AIC and LOO
- check a mixed model for overdispersion and zero-inflation
- assess convergence and singularity of a lme4 model
- get RMSE and fit indices for a statistical model
- evaluate goodness of fit across different model types

## When to choose
- you fit regression or mixed models in R and need consistent fit indices
- you want a unified interface for model quality metrics across many model classes
- you use the easystats ecosystem and want integrated model diagnostics

## When to avoid
- you work outside R or need deep-learning-specific benchmarking
- you need a general-purpose ML evaluation framework like scikit-learn metrics
- you only need simple descriptive statistics rather than model fit assessment

## Facets
- artifact type: library
- maturity: active
- function: testing, benchmarking, data-science
- domain: data-science, machine-learning, developer-tools
- platform: python
- tags: r-package, model-quality, goodness-of-fit, mixed-models, regression, easystats, cran, statistics

## Member repositories
- easystats/performance (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:46.685905+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:33:36.380727+00:00, confidence not recorded.
  - readme: https://github.com/easystats/performance (fetched 2026-08-28T04:03:46.685905+00:00, sha 857b18c77a9c)
  - homepage: https://easystats.github.io/performance/ (fetched 2026-08-29T12:38:17.873801+00:00, sha ecd0783aacb9)
- Data as of 2026-08-30T08:39:29.467469+00:00.