The four patient sets of a regional-consistency analysis

Fits the unadjusted two-sample Cox model on each set of the regional-consistency analysis, from columns you name: all patients, the region, region($G^*$) (the region without the true harmed subgroup, when truth.name is given) and region($\hat G$) (the region without the subgroup $\hat H$). The sets and their labels are those of mrct_case_study() and mrct_trial_analysis(), and print() and plot() draw on the same code.

Usage

mrct_four_sets(
  df,
  outcome.name,
  event.name,
  treat.name,
  region.name,
  in_Hhat = NULL,
  truth.name = NULL
)

# S3 method for class 'mrct_four_sets'
print(x, digits = 3, ...)

# S3 method for class 'mrct_four_sets'
as.data.frame(x, row.names = NULL, optional = FALSE, ...)

# S3 method for class 'mrct_four_sets'
plot(
  x,
  which = c("forest", "km"),
  xlim = c(0.3, 2),
  time_unit = NULL,
  analysis_time = NULL,
  ...
)

Arguments

df: A data frame with one row per patient.
outcome.name, event.name, treat.name: Columns: the time, the event indicator (1 = event) and the treatment (1 = experimental).
region.name: The region column (1 = in the region, 0 = not).
in_Hhat: Logical, one value per row: membership of $\hat H$, for instance get_dfpred(df, sg.harm = fit$sg.harm, version = 2)$treat.recommend == 0. NULL (the default) means nothing is declared: region($\hat G$) is the whole region.
truth.name: Optional column of the true harmed subgroup (1 = in $H^*$). It adds the region($G^*$) row and the 2 x 2 tables of $\hat H$ against $H^*$; without it neither appears.
x: An mrct_four_sets object.
digits: Digits for hazard ratios. Default 3.
...: Unused.
row.names, optional: Unused, as in as.data.frame().
which: Any of "forest", "km". Default both.
xlim: Hazard-ratio range of the forest plot. Default c(0.3, 2); intervals are clipped to it.
time_unit: Character. The label of the Kaplan-Meier time axis; NULL (the default) labels it "time".
analysis_time: The Kaplan-Meier axis's upper limit. NULL (the default) uses the longest follow-up in the trial.

Value

An object of class mrct_four_sets, a list with

sets: the table, also returned by as.data.frame(): set, label, n, n_exp, n_ctl, events_exp, events_ctl, and the Cox fit on the set: hr, lo, hi (Wald 95%), se_loghr. The rows are itt_all, itt_region, region_Gstar (with truth.name) and region_Ghat.
confusion: with truth.name, a list of two integer vectors c(TP, FP, FN, TN) of $\hat H$ against $H^*$, nonregion and region; else NULL.
trial, in_Hhat, and call_args, the column names.

Examples

set.seed(1)
n <- 400
d <- data.frame(time = rexp(n, 0.1), event = rbinom(n, 1, 0.8),
                treat = rbinom(n, 1, 0.5), region = rbinom(n, 1, 0.25),
                x = rbinom(n, 1, 0.3))
fs4 <- mrct_four_sets(d, "time", "event", "treat", region.name = "region",
                      in_Hhat = d$x == 1)
fs4
#> MRCT four sets: n = 400, region 'region'
#> 
#>  Set                        n   exp n/events ctl n/events HR    95% CI      
#>  All patients, ITT          400 180/141      220/177      0.918 0.733, 1.150
#>  Region, ITT                116 49/35        67/54        0.696 0.448, 1.080
#>  Region minus H-hat (G-hat)  91 42/29        49/39        0.673 0.408, 1.109
as.data.frame(fs4)[, c("set", "n", "hr", "lo", "hi")]
#>           set   n        hr        lo       hi
#> 1     itt_all 400 0.9180864 0.7326302 1.150489
#> 2  itt_region 116 0.6956959 0.4480358 1.080255
#> 3 region_Ghat  91 0.6729461 0.4084106 1.108827
plot(fs4, which = "forest")

The four patient sets of a regional-consistency analysis

Usage

Arguments

Value

See also

Examples