Logistic regression using p-values to select final model

Performs unadjusted logistic regression to identify candidate variables that fall under an p-value threshold (entry_criteria). Forward variable selection is performed to introduce variables into the model and retain if they fall within a more stringent criteria (retention_criteria).

Usage

pvalue_informed_regression(
  outcome,
  dataset,
  variables,
  entry_criteria = 0.2,
  retention_criteria = 0.1
)

Arguments

outcome

Outcome of interest

dataset

Dataframe that contains the trait and exposure variables

variables

Exposure variables of interest. Must be numeric or one-hot encoded

entry_criteria

P-value criteria for entry into the model. Default = 0.2

retention_criteria

P-value criteria for retention into the model. Default = 0.1

Value

Final regression model