Binary outcomes

In rifttable: Results Tables to Bridge the Rift Between Epidemiologists and Their Data

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

Example

The example uses the breastcancer data set from the risks package and compares the risk of death (a binary variable in this case) by categories of cancer stage.

library(rifttable)
library(dplyr)
data(breastcancer, package = "risks")

tibble::tribble(
  ~label,                      ~type,
  "**Absolute estimates**",    "",
  "Observations",              "total",
  "Outcomes",                  "outcomes",
  "Outcomes/Total",            "outcomes/total",
  "Cases/Controls",            "cases/controls",
  "Risk",                      "risk",
  "Risk (95% CI)",             "risk (ci)",
  "Outcomes (Risk)",           "outcomes (risk)",
  "Outcomes/Total (Risk)",     "outcomes/total (risk)",
  "",                          "",
  "**Comparative estimates**", "",
  "Risk ratio (95% CI)",       "rr",
  "Risk difference (95% CI)",  "rd",
  "Odds ratio (95% CI)",       "or"
) |>
  mutate(
    exposure = "stage",
    outcome = "death"
  ) |>
  rifttable(
    data = breastcancer,
    overall = TRUE
  ) |>
  rt_gt() # Formatted output

Absolute estimates per exposure category

type | Description | Options (arguments =) -----+-----------------+------------ "cases/controls" | Cases and non-cases (events and non-events); useful for case-control studies. "outcomes" | Outcome count. "outcomes (risk)" | A combination: Outcomes followed by risk in parentheses. "outcomes/total (risk)" | A combination: Outcomes slash total followed by risk in parentheses. "risk" | Risk (or prevalence), calculated as a proportion, i.e., outcomes divided by number of observations. Change between display as proportion or percent using the parameter risk_percent of rifttable(). "risk (ci)" | Risk with confidence interval (default: 95%): Wilson score interval for binomial proportions, see rifttable::scoreci().

Comparative estimates with confidence intervals

type | Description | Options (arguments =) -----+-----------------+------------ "irr" | Incidence rate ratio for count outcomes from Poisson regression model, with confidence interval (default: 95%). "or" | Odds ratio from logistic regression, with confidence interval (default: 95%). "rd" | Risk difference (or prevalence difference) from risks::riskdiff(), with confidence interval (default: 95%). | list(approach = "margstd_boot", bootrepeats = 2000) to request model fitting via marginal standardization with 2000 bootstraps. "rr" | Risk ratio (or prevalence ratio) from risks::riskratio(), with confidence interval (default: 95%). | See "rd".

rifttable documentation built on June 8, 2025, 1:52 p.m.