Skip to contents

Pairwise CoxPH model

Source: R/survival_coxph_pairwise.R
survival_coxph_pairwise.Rd

[Stable]

Summarize p-value, HR and CIs from stratified or unstratified CoxPH model.

Usage

s_coxph_pairwise(
  df,
  .ref_group,
  .in_ref_col,
  .var,
  is_event,
  strat = NULL,
  control = control_coxph()
)

a_coxph_pairwise(
  df,
  .ref_group,
  .in_ref_col,
  .var,
  is_event,
  strat = NULL,
  control = control_coxph()
)

coxph_pairwise(
  lyt,
  vars,
  ...,
  var_labels = "CoxPH",
  show_labels = "visible",
  table_names = vars,
  .stats = c("pvalue", "hr", "hr_ci"),
  .formats = NULL,
  .labels = NULL,
  .indent_mods = NULL
)

Arguments

df

(data frame)
data set containing all analysis variables.

.ref_group

(data frame or vector)
the data corresponding to the reference group.

.in_ref_col

(logical)
TRUE when working with the reference level, FALSE otherwise.

.var

(string)
single variable name that is passed by rtables when requested by a statistics function.

is_event

(logical)
TRUE if event, FALSE if time to event is censored.

strat

(character or NULL) variable names indicating stratification factors.

control

(list)
parameters for comparison details, specified by using
the helper function control_coxph(). Some possible parameter options are:

  • pval_method: (string)
    p-value method for testing hazard ratio = 1. Default method is "log-rank" which comes from survival::survdiff(), can also be set to "wald" or "likelihood" that comes from survival::coxph().

  • ties: (string)
    specifying the method for tie handling. Default is "efron", can also be set to "breslow" or "exact". See more in survival::coxph()

  • conf_level: (proportion)
    confidence level of the interval for HR.

lyt

(layout)
input layout where analyses will be added to.

vars

(character)
variable names for the primary analysis variable to be iterated over.

...

additional arguments for the lower level functions.

var_labels

character for label.

show_labels

label visibility: one of "default", "visible" and "hidden".

table_names

(character)
this can be customized in case that the same vars are analyzed multiple times, to avoid warnings from rtables.

.stats

(character)
statistics to select for the table.

.formats

(named character or list)
formats for the statistics.

.labels

(named character)
labels for the statistics (without indent).

.indent_mods

(named integer)
indent modifiers for the labels.

Value

The statistics are:

  • pvalue : p-value to test HR = 1.

  • hr : hazard ratio.

  • hr_ci : confidence interval for hazard ratio.

  • n_tot : total number of observations

  • n_tot_events : total number of events

Functions

  • s_coxph_pairwise(): Statistics Function which analyzes HR, CIs of HR and p-value with coxph model.

  • a_coxph_pairwise(): Formatted Analysis function which can be further customized by calling rtables::make_afun() on it. It is used as afun in rtables::analyze().

  • coxph_pairwise(): Analyze Function which adds the pairwise coxph analysis to the input layout. Note that additional formatting arguments can be used here.

Examples

library(scda)
library(dplyr)

ADTTE <- synthetic_cdisc_data("latest")$adtte
ADTTE_f <- ADTTE %>%
  filter(PARAMCD == "OS") %>%
  mutate(is_event = CNSR == 0)
df <- ADTTE_f %>%
  filter(ARMCD == "ARM A")
df_ref_group <- ADTTE_f %>%
  filter(ARMCD == "ARM B")

# Internal function - s_coxph_pairwise
if (FALSE) {
s_coxph_pairwise(df, df_ref_group, .in_ref_col = FALSE, .var = "AVAL", is_event = "is_event")
}

# Internal function - a_coxph_pairwise
if (FALSE) {
a_coxph_pairwise(df, df_ref_group, .in_ref_col = FALSE, .var = "AVAL", is_event = "is_event")
}

basic_table() %>%
  split_cols_by(var = "ARMCD", ref_group = "ARM A") %>%
  add_colcounts() %>%
  coxph_pairwise(
    vars = "AVAL",
    is_event = "is_event",
    var_labels = "Unstratified Analysis"
  ) %>%
  build_table(df = ADTTE_f)
#>                          ARM A       ARM B          ARM C    
#>                         (N=134)     (N=134)        (N=132)   
#> —————————————————————————————————————————————————————————————
#> Unstratified Analysis                                        
#>   p-value (log-rank)                 0.0334        <0.0001   
#>   Hazard Ratio                        1.39           2.75    
#>   95% CI                          (1.03, 1.90)   (2.05, 3.70)

basic_table() %>%
  split_cols_by(var = "ARMCD", ref_group = "ARM A") %>%
  add_colcounts() %>%
  coxph_pairwise(
    vars = "AVAL",
    is_event = "is_event",
    var_labels = "Stratified Analysis",
    strat = "SEX",
    control = control_coxph(pval_method = "wald")
  ) %>%
  build_table(df = ADTTE_f)
#>                        ARM A       ARM B          ARM C    
#>                       (N=134)     (N=134)        (N=132)   
#> ———————————————————————————————————————————————————————————
#> Stratified Analysis                                        
#>   p-value (wald)                   0.0487        <0.0001   
#>   Hazard Ratio                      1.36           2.73    
#>   95% CI                        (1.00, 1.86)   (2.02, 3.69)