junco (version 0.1.4)

odds_ratio: Odds ratio estimation

Description

A set of functions for Odds-Ratio (OR) calculation.

Usage

a_odds_ratio_j(
  df,
  .var,
  .df_row,
  ref_path,
  .spl_context,
  ...,
  .stats = NULL,
  .formats = NULL,
  .labels = NULL,
  .indent_mods = NULL
)
s_odds_ratio_j(
  df,
  .var,
  .ref_group,
  .in_ref_col,
  .df_row,
  variables = list(arm = NULL, strata = NULL),
  conf_level = 0.95,
  groups_list = NULL,
  na_if_no_events = TRUE,
  method = c("exact", "approximate", "efron", "breslow", "cmh")
)

Value

• a_odds_ratio_j() returns the corresponding list with formatted rtables::CellValue().

• s_odds_ratio_j() returns a named list with the statistics or_ci (containing est, lcl, and ucl), pval and n_tot.

Arguments

df

(data.frame)
input data frame.

.var

(string)
name of the response variable.

.df_row

(data.frame)
data frame containing all rows.

ref_path

(character)
path to the reference group.

.spl_context

(environment)
split context environment.

...

Additional arguments passed to the statistics function.

.stats

(character)
statistics to calculate.

.formats

(list)
formats for the statistics.

.labels

(list)
labels for the statistics.

.indent_mods

(list)
indentation modifications for the statistics.

.ref_group

(data.frame)
reference group data frame.

.in_ref_col

(logical)
whether the current column is the reference column.

variables

(list)
list with arm and strata variable names.

conf_level

(numeric)
confidence level for the confidence interval.

groups_list

(list)
list of groups for combination.

na_if_no_events

(flag)
whether the point estimate should be NA if there are no events in one arm. The p-value and confidence interval will still be computed.

method

(string)
whether to use the correct ('exact') calculation in the conditional likelihood or one of the approximations, or the CMH method. See survival::clogit() for details.

Functions

• a_odds_ratio_j(): Formatted analysis function which is used as afun. Note that the junco specific ref_path and .spl_context arguments are used for reference column information.

• s_odds_ratio_j(): Statistics function which estimates the odds ratio between a treatment and a control. A variables list with arm and strata variable names must be passed if a stratified analysis is required.

Examples

set.seed(12)
dta <- data.frame(
  rsp = sample(c(TRUE, FALSE), 100, TRUE),
  grp = factor(rep(c("A", "B"), each = 50), levels = c("A", "B")),
  strata = factor(sample(c("C", "D"), 100, TRUE))
)

a_odds_ratio_j(
  df = subset(dta, grp == "A"),
  .var = "rsp",
  ref_path = c("grp", "B"),
  .spl_context = data.frame(
    cur_col_split = I(list("grp")),
    cur_col_split_val = I(list(c(grp = "A"))),
    full_parent_df = I(list(dta))
  ),
  .df_row = dta
)


l <- basic_table() |>
  split_cols_by(var = "grp") |>
  analyze(
    "rsp",
    afun = a_odds_ratio_j,
    show_labels = "hidden",
    extra_args = list(
      ref_path = c("grp", "B"),
      .stats = c("or_ci", "pval")
    )
  )

build_table(l, df = dta)

l2 <- basic_table() |>
  split_cols_by(var = "grp") |>
  analyze(
    "rsp",
    afun = a_odds_ratio_j,
    show_labels = "hidden",
    extra_args = list(
      variables = list(arm = "grp", strata = "strata"),
      method = "cmh",
      ref_path = c("grp", "A"),
      .stats = c("or_ci", "pval")
    )
  )

build_table(l2, df = dta)
s_odds_ratio_j(
  df = subset(dta, grp == "A"),
  .var = "rsp",
  .ref_group = subset(dta, grp == "B"),
  .in_ref_col = FALSE,
  .df_row = dta
)

s_odds_ratio_j(
  df = subset(dta, grp == "A"),
  .var = "rsp",
  .ref_group = subset(dta, grp == "B"),
  .in_ref_col = FALSE,
  .df_row = dta,
  variables = list(arm = "grp", strata = "strata")
)

s_odds_ratio_j(
  df = subset(dta, grp == "A"),
  method = "cmh",
  .var = "rsp",
  .ref_group = subset(dta, grp == "B"),
  .in_ref_col = FALSE,
  .df_row = dta,
  variables = list(arm = "grp", strata = c("strata"))
)