undi: Test for Unjustified Disparate Impact

Within specified values of sensitivity parameters, find the ones that achieve minimum/maximum sensitivity results

gridsens(pol, qs = c(0, 0.4, 0.5, 0.6, 1), dps = c(0, log(2)), d0s = c(0,
  log(2)), d1s = c(0, log(2)), params_grid = NULL, base_group = NULL,
  minority_groups = NULL, allow_sgv = FALSE, controls = NULL,
  fit_fn = "logit_coef", include_benchmark = FALSE, verbose = TRUE)

`pol`	object of class `policy`
`qs`	vector q values to search
`dps`	values to search for change in log-odds of treat = 1 if u = 1
`d0s`	values to search for change in log-odds of response = 1 if treat = 0 and u = 1
`d1s`	values to search for change in log-odds of response = 1 if treat = 1 and u = 1
`params_grid`	(Optional) data frame with columns `qb, qm, ab, am, d0b, d0m, d1b, d1m` indicating the parameter combinations to be searched over. If specified, the parameter range argments (`qs` through `d1s`) are ignored.
`base_group`	(Optional) single group that acts as the pivot/base; by default, if the grouping variable is a factor, set to the first level, otherwise set to the first of sorted unique values
`minority_groups`	(Optional) groups to compare to the base group; by default, set to every unique value other than the base group
`allow_sgv`	logical; whether to allow for subgroup validity; i.e., if `TRUE`, the delta parameters (`dp`, `d0`, `d1`) will be allowed to vary between base/minority groups, but if `FALSE`, a single value for each delta parameter will be used for each base/minority pair
`controls`	vector of legitimate controls to use; the ones specified within the policy object will be used if not specified
`fit_fn`	string indicating the rad estimation model/procedure used. `_coef` methods use models without interaction between risk and group, and return the coeficient on group membership. `_avg` methods will fit more flexible models (possibly with interactions), and compute average ratios across the population. (TODO: better documentation is expected)
`include_benchmark`	logical; whether to include the two extreme benchmark test results (default: FALSE)
`verbose`	whether or not to print debug messages (0 = none, 1 = results only, 2 = everything)

a list-type object of class gridsens with the following elements

`results`	`tidy` dataframe of second-stage model coefficients after searching for min/max values across specified sensitivy parameter values, independently for each minority group
`grid`	results from full grid
`base_case`	result from `compute_rad` on base policy with specified groups and controls
`base_group`	base group used in analysis