Summary of HAL fits

Summary of HAL fits

# S3 method for hal9001
summary(
  object,
  lambda = NULL,
  only_nonzero_coefs = TRUE,
  remove_redundant_duplicates = TRUE,
  round_cutoffs = 4,
  ...
)

Arguments

object	An object of class hal9001, containing the results of fitting the Highly Adaptive Lasso, as produced by fit_hal.
lambda	Optional numeric value of the lambda tuning parameter, for which corresponding coefficient values to be summarized. Defaults to CV-optimal value lambda_star, or the minimum value of lambda_star.
only_nonzero_coefs	A logical specifying whether the summary should include only non-zero coefficients.
remove_redundant_duplicates	A logical specifying whether the summary should remove redundant indicator basis function duplicates. If basis functions are duplicated, then one coefficient will correspond to all of the duplicates. If remove_redundant_duplicates is TRUE, then the shorter basis function is retained. For example, the same coefficient may correspond to terms "I(age >= 50)*I(bmi >= 18)", "I(age >= 50)", and "I(education >= 16)", which means these basis functions all yield the same result. When remove_redundant_duplicates is TRUE, the second basis function is omitted due to the duplicated term "I(age >= 50)".
round_cutoffs	An integer indicating the number of decimal places to be used for rounding term cutoff values.
...	Additional arguments passed to summary as necessary.

Value

A list summarizing a hal9001 object's coefficients.

Details

Method for summarizing the coefficients of the Highly Adaptive Lasso estimator in terms of the basis functions corresponding to covariates and interactions of covariates, returned as a single S3 object of class hal9001.