performance0.12.4 package

Assessment of Regression Models Performance

check_autocorrelation

Check model for independence of residuals.

check_clusterstructure

Check suitability of data for clustering

check_collinearity

Check for multicollinearity of model terms

check_convergence

Convergence test for mixed effects models

check_dag

Check correct model adjustment for identifying causal effects

item_split_half

Split-Half Reliability

looic

LOO-related Indices for Bayesian regressions.

model_performance.ivreg

Performance of instrumental variable regression models

model_performance.kmeans

Model summary for k-means clustering

model_performance.lavaan

Performance of lavaan SEM / CFA Models

r2_mckelvey

McKelvey & Zavoinas R2

binned_residuals

Binned residuals for binomial logistic regression

check_distribution

Classify the distribution of a model-family using machine learning

check_factorstructure

Check suitability of data for Factor Analysis (FA) with Bartlett's Tes...

check_heterogeneity_bias

Check model predictor for heterogeneity bias

check_heteroscedasticity

Check model for (non-)constant error variance

check_homogeneity

Check model for homogeneity of variances

check_itemscale

Describe Properties of Item Scales

check_model

Visual check of model assumptions

check_multimodal

Check if a distribution is unimodal or multimodal

check_normality

Check model for (non-)normality of residuals.

check_outliers

Outliers detection (check for influential observations)

check_overdispersion

Check overdispersion (and underdispersion) of GL(M)M's

check_predictions

Posterior predictive checks

icc

Intraclass Correlation Coefficient (ICC)

check_residuals

Check uniformity of simulated residuals

check_singularity

Check mixed models for boundary fits

check_sphericity

Check model for violation of sphericity

check_symmetry

Check distribution symmetry

check_zeroinflation

Check for zero-inflation in count models

classify_distribution

Classify the distribution of a model-family using machine learning

compare_performance

Compare performance of different models

cronbachs_alpha

Cronbach's Alpha for Items or Scales

display.performance_model

Print tables in different output formats

item_difficulty

Difficulty of Questionnaire Items

item_discrimination

Discrimination of Questionnaire Items

item_intercor

Mean Inter-Item-Correlation

item_reliability

Reliability Test for Items or Scales

performance-package

performance: An R Package for Assessment, Comparison and Testing of St...

model_performance.lm

Performance of Regression Models

model_performance.merMod

Performance of Mixed Models

model_performance

Model Performance

model_performance.rma

Performance of Meta-Analysis Models

model_performance.stanreg

Performance of Bayesian Models

performance_accuracy

Accuracy of predictions from model fit

performance_aicc

Compute the AIC or second-order AIC

performance_cv

Cross-validated model performance

performance_hosmer

Hosmer-Lemeshow goodness-of-fit test

performance_logloss

Log Loss

performance_mae

Mean Absolute Error of Models

performance_mse

Mean Square Error of Linear Models

r2_bayes

Bayesian R2

performance_pcp

Percentage of Correct Predictions

performance_rmse

Root Mean Squared Error

performance_roc

Simple ROC curve

performance_rse

Residual Standard Error for Linear Models

performance_score

Proper Scoring Rules

r2_coxsnell

Cox & Snell's R2

r2_efron

Efron's R2

r2_ferrari

Ferrari's and Cribari-Neto's R2

r2_kullback

Kullback-Leibler R2

r2_loo

LOO-adjusted R2

r2_mcfadden

McFadden's R2

r2_mlm

Multivariate R2

r2_nagelkerke

Nagelkerke's R2

r2_nakagawa

Nakagawa's R2 for mixed models

r2_somers

Somers' Dxy rank correlation for binary outcomes

r2_tjur

Tjur's R2 - coefficient of determination (D)

r2_xu

Xu' R2 (Omega-squared)

r2_zeroinflated

R2 for models with zero-inflation

r2

Compute the model's R2

reexports

Objects exported from other packages

simulate_residuals

Simulate randomized quantile residuals from a model

test_performance

Test if models are different

Utilities for computing measures to assess model quality, which are not directly provided by R's 'base' or 'stats' packages. These include e.g. measures like r-squared, intraclass correlation coefficient (Nakagawa, Johnson & Schielzeth (2017) <doi:10.1098/rsif.2017.0213>), root mean squared error or functions to check models for overdispersion, singularity or zero-inflation and more. Functions apply to a large variety of regression models, including generalized linear models, mixed effects models and Bayesian models. References: Lüdecke et al. (2021) <doi:10.21105/joss.03139>.

  • Maintainer: Daniel Lüdecke
  • License: GPL-3
  • Last published: 2024-10-18