Summarise a matchatr fit

Description

Prints the odds-ratio table of a fitted unmatched case-control logistic regression — one row per model term, on the odds-ratio scale with a Wald confidence interval — under a short header naming the design, estimator, and variance source.

Usage

## S3 method for class 'matchatr_fit'
summary(object, conf.level = 0.95, robust = FALSE, ...)

Arguments

object	A matchatr_fit whose model is a fitted binomial glm.
conf.level	Numeric confidence level in (0, 1). Default 0.95.
robust	Logical; use the Huber-White sandwich standard error. Default FALSE.
…	Unused; present for S3 consistency.

Details

The intercept is shown but flagged as non-interpretable: it is not a baseline risk in a case-control sample. Standard errors are model-based by default, or Huber-White robust when robust = TRUE.

Value

Invisibly, the odds-ratio data.table (as returned by tidy.matchatr_fit() with exponentiate = TRUE).

See Also

matcha(), tidy.matchatr_fit(), contrast()

Examples

library("matchatr")

set.seed(1)
df <- data.frame(
  case = rep(c(1, 0), each = 100),
  x = rbinom(200, 1, 0.4),
  age = rnorm(200, 50, 10)
)
fit <- matcha(df, outcome = "case", exposure = "x",
              design = unmatched_cc(), confounders = ~ age)
summary(fit)

<matchatr_fit> summary
 Design:     Unmatched case-control
 Estimator:  logistic  (engine: glm_logistic)
 Std. error: model-based

Conditional odds ratios (95% Wald CI):
          term  estimate  std.error  statistic   p.value  conf.low conf.high
        <char>     <num>      <num>      <num>     <num>     <num>     <num>
1: (Intercept) 1.3289105 0.74085320  0.3838270 0.7011067 0.3110859  5.676899
2:           x 1.1270782 0.28743963  0.4161870 0.6772732 0.6416305  1.979808
3:         age 0.9933368 0.01429163 -0.4677933 0.6399324 0.9658984  1.021555

Note: the intercept is not an interpretable baseline risk in a case-control sample.