The summaries are always in the form of a data frame
conf_interval()--- displays coefficients and their confidence intervalsR2()--- R-squared of a model together with related measures such as F, adjusted R-squared, the p-value, and degrees of freedom used in calculating the p-value.regression_summary()-- A regression report in data-frame format.anova_summary()--- An ANOVA report in data-frame format. If only one model is passed as an argument, the data frame will have one line per model term. If multiple models are given as arguments, the ANOVA report will show the increments from one model to the next.
Usage
conf_interval(model, level = 0.95, show_p = FALSE)
R2(model)
regression_summary(model)
anova_summary(...)Arguments
- model
A model as produced by
model_train(),lm(),glm(), and so on- level
Confidence level to use in
conf_interval()(default: 0.95)- show_p
For
conf_interval(), append the p-value to the report.- ...
One or more models (for ANOVA)
Details
Many of these are wrappers around broom::tidy() used to
emphasize to students that the results are a summary in the form of a regression
report, similar to the summaries produced by stats::confint(), stats::coef(), etc.
Examples
Model <- FEV |> model_train(FEV ~ age + smoker)
Model |> conf_interval()
#> # A tibble: 3 × 4
#> term .lwr .coef .upr
#> <chr> <dbl> <dbl> <dbl>
#> 1 (Intercept) 0.207 0.367 0.527
#> 2 age 0.215 0.231 0.247
#> 3 smokersmoker -0.368 -0.209 -0.0504
Model |> R2()
#> n k Rsquared F adjR2 p df.num df.denom
#> 1 654 2 0.5765875 443.2539 0.5752867 0 2 651
Model |> anova_summary()
#> # A tibble: 3 × 6
#> term df sumsq meansq statistic p.value
#> <chr> <int> <dbl> <dbl> <dbl> <dbl>
#> 1 age 1 281. 281. 880. 5.54e-123
#> 2 smoker 1 2.14 2.14 6.70 9.86e- 3
#> 3 Residuals 651 208. 0.319 NA NA