Create clones for CCW analysis — create

Pass a one-row-per-patient data.frame and get back a data.frame with one row per clone.

create_clones(
  df,
  id,
  event,
  time_to_event,
  exposure,
  time_to_exposure,
  ced_window = NULL
)

Arguments

df: A data.frame with one row per patient.
id: The name of the column in df that contains the patient identifier.
event: The name of the column in df that contains the event of interest.
time_to_event: The name of the column in df that contains the time to event.
exposure: The name of the column in df that contains the exposure.
time_to_exposure: The name of the column in df that contains the time to exposure.
ced_window: The date at which the clinical eligibility window closes. Can be left empty, in which case the clinical eligibility window is assumed to be part of exposure and time_to_exposure

Value

A data.frame with one row per clone.

References

Maringe, Camille, et al. "Reflection on modern methods: trial emulation in the presence of immortal-time bias. Assessing the benefit of major surgery for elderly lung cancer patients using observational data." International journal of epidemiology 49.5 (2020): 1719-1729.

Examples


# Load the toy dataset
data(toy_df)

# Create clones
clones <- create_clones(toy_df, 
                        id = "id", 
                        event = "death", 
                        time_to_event = "fup_obs", 
                        exposure = "surgery", 
                        time_to_exposure = "timetosurgery", 
                        ced_window = 365.25/2)