Control standard_errors parameters

se_control(
  se_method = "subsample",
  subsample_percent = 0.2,
  num_bs = 100,
  draw_weights = F,
  sampling_method = "subsampleRows",
  parallel_thresh = 1e+05,
  ...
)

Arguments

se_method

Method to use for standard errors, either "weighted_bootstrap", "subsample", "bootstrap" or "rq_sample" (the last one is fully customized per the other se_control parameters) along with a specified subsampling method and subsample percent. If specifying "custom", must also specify subsampling_percent and draw_weights. If you specify "subsample", subsampling percent defaults to 0.2, but can be changed.

subsample_percent

A number between 0 and one, specifying the percent of the data to subsample for standard error calculations

num_bs

Number of bootstrap iterations to use, defaults to 100.

draw_weights

Whether to use random exponential weights for bootstrap, either TRUE or FALSE

sampling_method

One of "leaveRows", "subsampleRows", or "bootstrapRows".

parallel_thresh

threshold for when to use parallel, based on nrow(X) * num_bs. To always use parallel, set to 0. Designed to avoid slow overhead when problem is relatively small.

...

Other arguments, ignored for now leaveRows doesn't resample rows at all. subsampleRows samples without replacement given some percentage of the data (specified via subsample_percent), and bootstrapRows samples with replacement.

Details

se_control control parameters to pass to the control arguments of quantreg_spacing, the lower-level function called by standard_errors.