Get Protocol Variables for Standardisation

This function identifies which among the candidate protocol variables are significantly associated with the exposure to be standardised. The selection is based on ANOVA p-values (< 0.2). Model outputs are exported to files for transparency and quality control.

Usage

get_protocol_var(
  data,
  var_to_std,
  protocol_vars,
  covariates,
  folder,
  group,
  export_check_model,
  p_thresh
)

Arguments

data

A data.frame containing the exposure, protocol variables, and optional covariates.

var_to_std

A character string giving the name of the variable to be standardised.

protocol_vars

A character vector of names of potential protocol variables.

covariates

A character vector of additional covariates to include in the model (not corrected for).

folder

A character string giving the directory where outputs (model summary, ANOVA table, optional model check) will be saved.

group

A character string or vector used for naming the output files (typically the exposure variable name).

export_check_model

Logical. If TRUE, exports model diagnostic plots from performance::check_model(). Default is FALSE.

p_thresh

Numeric. The p-value threshold used to select protocol variables for adjustment. Default is 0.05.

Value

A character vector containing the names of the protocol variables with p-value < 0.2, to be used for standardisation.

See also

Anova, tidy, check_model, export