This function uses car::Anova with argument
`type = "III"`

to calculate global p-values for categorical variables.

# S3 method for tbl_regression
add_global_p(
x,
include = x$table_body$variable[x$table_body$var_type %in% c("categorical",
"interaction")],
type = NULL,
keep = FALSE,
quiet = NULL,
...,
terms = NULL
)

## Arguments

x |
Object with class `tbl_regression` from the
tbl_regression function |

include |
Variables to calculate global p-value for. Input may be a vector of
quoted or unquoted variable names. tidyselect and gtsummary select helper
functions are also accepted. Default is `NULL` , which adds global p-values
for all categorical and interaction terms. |

type |
Type argument passed to car::Anova. Default is `"III"` |

keep |
Logical argument indicating whether to also retain the individual
p-values in the table output for each level of the categorical variable.
Default is `FALSE` |

quiet |
Logical indicating whether to print messages in console. Default is
`FALSE` |

... |
Additional arguments to be passed to car::Anova |

terms |
DEPRECATED. Use `include=` argument instead. |

## Value

A `tbl_regression`

object

## Note

If a needed class of model is not supported by
car::Anova, please create a
GitHub Issue to request support.

## Example Output

## See also

## Author

Daniel D. Sjoberg

## Examples

#> Global p-values for variable(s) `include = "grade"` were calculated with
#> `car::Anova(x$model_obj, type = "III")`