h_response_subgroups: Helper functions for tabulating binary response by subgroup

In tern: Create Common TLGs Used in Clinical Trials

Helper functions for tabulating binary response by subgroup

Description

Helper functions that tabulate in a data frame statistics such as response rate and odds ratio for population subgroups.

Usage

h_proportion_df(rsp, arm)

h_proportion_subgroups_df(
  variables,
  data,
  groups_lists = list(),
  label_all = "All Patients"
)

h_odds_ratio_df(rsp, arm, strata_data = NULL, conf_level = 0.95, method = NULL)

h_odds_ratio_subgroups_df(
  variables,
  data,
  groups_lists = list(),
  conf_level = 0.95,
  method = NULL,
  label_all = "All Patients"
)

Arguments

rsp	(logical) vector indicating whether each subject is a responder or not.
arm	(factor) the treatment group variable.
variables	(named list of string) list of additional analysis variables.
data	(data.frame) the dataset containing the variables to summarize.
groups_lists	(named list of list) optionally contains for each subgroups variable a list, which specifies the new group levels via the names and the levels that belong to it in the character vectors that are elements of the list.
label_all	(string) label for the total population analysis.
strata_data	(factor, data.frame, or NULL) required if stratified analysis is performed.
conf_level	(proportion) confidence level of the interval.
method	(string or NULL) specifies the test used to calculate the p-value for the difference between two proportions. For options, see test_proportion_diff(). Default is NULL so no test is performed.

Details

Main functionality is to prepare data for use in a layout-creating function.

Value

• h_proportion_df() returns a data.frame with columns arm, n, n_rsp, and prop.

• h_proportion_subgroups_df() returns a data.frame with columns arm, n, n_rsp, prop, subgroup, var, var_label, and row_type.

• h_odds_ratio_df() returns a data.frame with columns arm, n_tot, or, lcl, ucl, conf_level, and optionally pval and pval_label.

• h_odds_ratio_subgroups_df() returns a data.frame with columns arm, n_tot, or, lcl, ucl, conf_level, subgroup, var, var_label, and row_type.

Functions

• h_proportion_df(): Helper to prepare a data frame of binary responses by arm.

• h_proportion_subgroups_df(): Summarizes proportion of binary responses by arm and across subgroups in a data frame. variables corresponds to the names of variables found in data, passed as a named list and requires elements rsp, arm and optionally subgroups. groups_lists optionally specifies groupings for subgroups variables.

• h_odds_ratio_df(): Helper to prepare a data frame with estimates of the odds ratio between a treatment and a control arm.

• h_odds_ratio_subgroups_df(): Summarizes estimates of the odds ratio between a treatment and a control arm across subgroups in a data frame. variables corresponds to the names of variables found in data, passed as a named list and requires elements rsp, arm and optionally subgroups and strata. groups_lists optionally specifies groupings for subgroups variables.

Examples

library(dplyr)
library(forcats)

adrs <- tern_ex_adrs
adrs_labels <- formatters::var_labels(adrs)

adrs_f <- adrs %>%
  filter(PARAMCD == "BESRSPI") %>%
  filter(ARM %in% c("A: Drug X", "B: Placebo")) %>%
  droplevels() %>%
  mutate(
    # Reorder levels of factor to make the placebo group the reference arm.
    ARM = fct_relevel(ARM, "B: Placebo"),
    rsp = AVALC == "CR"
  )
formatters::var_labels(adrs_f) <- c(adrs_labels, "Response")

h_proportion_df(
  c(TRUE, FALSE, FALSE),
  arm = factor(c("A", "A", "B"), levels = c("A", "B"))
)

h_proportion_subgroups_df(
  variables = list(rsp = "rsp", arm = "ARM", subgroups = c("SEX", "BMRKR2")),
  data = adrs_f
)

# Define groupings for BMRKR2 levels.
h_proportion_subgroups_df(
  variables = list(rsp = "rsp", arm = "ARM", subgroups = c("SEX", "BMRKR2")),
  data = adrs_f,
  groups_lists = list(
    BMRKR2 = list(
      "low" = "LOW",
      "low/medium" = c("LOW", "MEDIUM"),
      "low/medium/high" = c("LOW", "MEDIUM", "HIGH")
    )
  )
)

# Unstratatified analysis.
h_odds_ratio_df(
  c(TRUE, FALSE, FALSE, TRUE),
  arm = factor(c("A", "A", "B", "B"), levels = c("A", "B"))
)

# Include p-value.
h_odds_ratio_df(adrs_f$rsp, adrs_f$ARM, method = "chisq")

# Stratatified analysis.
h_odds_ratio_df(
  rsp = adrs_f$rsp,
  arm = adrs_f$ARM,
  strata_data = adrs_f[, c("STRATA1", "STRATA2")],
  method = "cmh"
)

# Unstratified analysis.
h_odds_ratio_subgroups_df(
  variables = list(rsp = "rsp", arm = "ARM", subgroups = c("SEX", "BMRKR2")),
  data = adrs_f
)

# Stratified analysis.
h_odds_ratio_subgroups_df(
  variables = list(
    rsp = "rsp",
    arm = "ARM",
    subgroups = c("SEX", "BMRKR2"),
    strata = c("STRATA1", "STRATA2")
  ),
  data = adrs_f
)

# Define groupings of BMRKR2 levels.
h_odds_ratio_subgroups_df(
  variables = list(
    rsp = "rsp",
    arm = "ARM",
    subgroups = c("SEX", "BMRKR2")
  ),
  data = adrs_f,
  groups_lists = list(
    BMRKR2 = list(
      "low" = "LOW",
      "low/medium" = c("LOW", "MEDIUM"),
      "low/medium/high" = c("LOW", "MEDIUM", "HIGH")
    )
  )
)

tern documentation built on Sept. 24, 2024, 9:06 a.m.