Propensity-score overlap diagnostics — morie_matching

Reports the propensity-score range overlap between treated and control, the number / percentage of units off support, and the IPW effective sample size.

Usage

morie_matching_overlap(data, treatment, covariates, ps = NULL)

Arguments

data: Data frame.
treatment: Binary treatment column.
covariates: Character vector of covariates.
ps: Optional propensity scores. When supplied they REPLACE the fitted model and become the matching distance directly, aligned to the rows that survive the NA drop.

Value

A list with ps_summary (per-group quantiles), overlap_region, n_off_support, pct_off_support, and effective_sample_size.

Examples

# \donttest{
set.seed(1)
df <- data.frame(y = rnorm(200), d = rbinom(200, 1, 0.4),
                 x1 = rnorm(200), x2 = rnorm(200))
morie_matching_overlap(df, "d", c("x1", "x2"))
#> $ps_summary
#> $ps_summary$treated
#>        0%       25%       50%       75%      100% 
#> 0.3232241 0.4066149 0.4415529 0.4775863 0.5805204 
#> 
#> $ps_summary$control
#>        0%       25%       50%       75%      100% 
#> 0.2956479 0.3957489 0.4306308 0.4693225 0.5570639 
#> 
#> 
#> $overlap_region
#>     lower     upper 
#> 0.3232241 0.5570639 
#> 
#> $n_off_support
#> [1] 10
#> 
#> $pct_off_support
#> [1] 5
#> 
#> $effective_sample_size
#> [1] 192.2308
#> 
# }