Compare support (overlap) rules

Flags patients with weak support under several rules and measures how well the rules agree. Built-in rules use the propensity score of a ps_data object; any other rule (for example an isolation-forest tail flag) can be supplied as a logical vector.

Usage

ps_support(x, flags = list(), trim = c(0.1, 0.9), common = TRUE)

Arguments

x

A ps_data object with a score and treatment column. The score of a ps_match() object built with scale = "logit" is a logit, and is back-transformed with stats::plogis(), so trim and the common-support interval are on the probability scale.

flags

Optional named list of extra logical vectors, one element per row of x$data, TRUE meaning the rule would drop that patient. The names "trim" and "common" belong to the built-in rules and are refused.

trim

Length-2 numeric, or NULL. Adds the rule "score outside [trim[1], trim[2]]". Both values must lie in [0, 1], increasing. Default c(0.1, 0.9).

common

Logical; add the rule "score outside the range occupied by both groups" (common support).

Value

A ps_support / ps_data object. $data is x$data plus one logical column weak_<rule> per rule. $tables$counts gives the number flagged per rule (n_weak), the number of rows that rule judged (n) and the number it did not (n_excluded): rows with a missing treatment or score, plus any missing values in a rule supplied through flags. $meta$n_excluded counts the rows with a missing treatment or score; $tables$agreement gives, for every pair of rules, n_both, n_neither, pct_agree, Cohen kappa and jaccard (overlap of the two dropped sets). $meta$common_support is the interval used, on the probability scale. $meta$scale is the scale of score_col, carried from x ("probability" when x records none).

Details

Trimming changes the estimand. Dropping the patients a rule flags leaves a population defined by the rule: an effect estimated after trimming at c(0.1, 0.9), or after restricting to common support, describes the patients with adequate overlap, not the full sample, the treated or the controls. Name that population when you report it. This function only flags patients; it drops nobody.

A patient with a missing treatment or a missing score cannot be judged. Those rows are left out of the common-support interval and every rule, get a missing weak_<rule> flag, and one warning states how many there are.

Examples

dta <- sample_ps_data(n = 200, seed = 3)[, c("id", "tavr", "age", "ef")]
sup <- ps_support(ps_logistic(tavr ~ age + ef, dta))
sup$tables$agreement
#>   rule_a rule_b   n n_a n_b n_both n_neither pct_agree     kappa   jaccard
#> 1 common   trim 400  17   7      7       383      97.5 0.5727409 0.4117647