Investigating the fit of statistical models to data often involves selecting the best fitting model amongst many competing models. This function helps report indices of model fit for various models. Reports the type of different R objects . For a list of supported objects, see report()).

## Usage

report_performance(x, table = NULL, ...)

## Arguments

x

The R object that you want to report (see list of of supported objects above).

table

A table obtained via report_table(). If not provided, will run it.

...

Arguments passed to or from other methods.

## Value

An object of class report_performance().

## Examples

# \donttest{
library(report)

# GLMs
report_performance(lm(Sepal.Length ~ Petal.Length * Species, data = iris))
#> The model explains a statistically significant and substantial proportion of variance (R2 = 0.84, F(5, 144) = 151.71, p < .001, adj. R2 = 0.83)
report_performance(glm(vs ~ disp, data = mtcars, family = "binomial"))
#> The model's explanatory power is substantial (Tjur's R2 = 0.53)

# Mixed models
if (require("lme4")) {
model <- lme4::lmer(Sepal.Length ~ Petal.Length + (1 | Species), data = iris)
report_performance(model)
}
#> Package 'merDeriv' needs to be installed to compute confidence intervals
#>   for random effect parameters.
#> The model's total explanatory power is substantial (conditional R2 = 0.97) and the part related to the fixed effects alone (marginal R2) is of 0.66

# Bayesian models
if (require("rstanarm")) {
model <- stan_glm(Sepal.Length ~ Species, data = iris, refresh = 0, iter = 600)
report_performance(model)
}
#> The model's explanatory power is substantial (R2 = 0.61, 95% CI [0.52, 0.69], adj. R2 = 0.61)

# Structural Equation Models (SEM)
if (require("lavaan") && packageVersion("effectsize") >= "0.6.0.1" && FALSE) {
structure <- " ind60 =~ x1 + x2 + x3
dem60 =~ y1 + y2 + y3
dem60 ~ ind60 "
model <- lavaan::sem(structure, data = PoliticalDemocracy)
report_performance(model)
}
# }