Jackknife mars wrapper — sample

This is a wrapper around mars() to perform leave-one-out jackknife estimation for a single omitted unit.

sample_jackknife(
  leave_out,
  data,
  studyID,
  effectID,
  sample_size,
  effectsize_type = NULL,
  formula = NULL,
  variable_names = NULL,
  effectsize_name = NULL,
  estimation_method = "REML",
  variance = NULL,
  varcov_type,
  weights = NULL,
  structure = "UN",
  intercept = FALSE,
  missing = "remove",
  optim_method = "L-BFGS-B",
  robustID = NULL,
  multivariate_covs = NULL,
  jackknife_target = c("complete_data", "beta_selection", "beta_binomial",
    "logistic_selection"),
  publication_bias_args = list(),
  lasso = FALSE,
  lasso_args = list(lambda_grid = 10^seq(-3, 1, length.out = 10), K = 5,
    all_lasso_metrics = FALSE, lambda_tolerance = 0),
  tol = 1e-10,
  ...
)

Arguments

leave_out: Unit to omit from the dataset. For single-level models this is a row index. For multilevel models this is one highest-level cluster value.
data: Data used for analysis.
studyID: Character string representing the study ID.
effectID: Character string representing the effect size ID.
sample_size: Character string representing the sample size of the studies.
effectsize_type: Type of effect size being analyzed.
formula: The formula used for specifying the fixed and random structure.
variable_names: Vector of character strings representing the attributes with correlations. The attributes that are correlated should be separated by an underscore.
effectsize_name: Character string representing the name of the effect size column in the data.
estimation_method: Type of estimation used, either "REML" or "MLE".
variance: Character string representing the variance column name.
varcov_type: Type of variance covariance matrix computed.
weights: User specified matrix of weights for analysis.
structure: Between studies covariance structure.
intercept: Whether a model intercept should be specified.
missing: Whether missing data should be removed, or kept.
optim_method: Optimization method passed to optim().
robustID: A character vector specifying the cluster group to use for robust standard errors.
multivariate_covs: A one-sided formula for multivariate analysis covariates.
jackknife_target: Analysis to fit after each leave-one-out omission. Use "complete_data" for the standard MARS re-fit, or one of "beta_selection", "beta_binomial", or "logistic_selection" to refit the omitted dataset and then apply publication_bias with that method.
publication_bias_args: Optional named list of extra arguments passed to publication_bias when jackknife_target is a publication-bias method.
lasso: TRUE/FALSE indicator that specifies if LASSO results are returned.
lasso_args: A list of LASSO specific arguments.
tol: Tolerance of the optimization.
...: Additional arguments passed to mars for each jackknife re-fit.